Sustainable Computing-Informatics & Systems最新文献_第2页

EAURP: An energy-efficient and trust-aware unobservable routing protocol for secure mobile Ad Hoc networks EAURP：用于安全移动Ad Hoc网络的节能且信任感知的不可观察路由协议

IF 5.7 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-12-17 DOI: 10.1016/j.suscom.2025.101285

A. Chandra , A.S.N. Chakravarthy

Mobile ad hoc wireless networks (MANETs) are decentralized, lacking fixed infrastructure, which enables dynamic and flexible communication between mobile nodes. However, these networks face challenges such as limited energy resources, frequent topology changes, and performance degradation caused by node misbehavior. Existing protocols like AODV have significant limitations, including a lack of energy awareness, an inability to detect malicious behavior, and the absence of secure transmission mechanisms. These weaknesses lead to rapid energy depletion and increased vulnerability to attacks. To address these issues, this paper proposes a novel energy-aware unobservable routing protocol. The new protocol introduces custom packet types, such as PT_NID, PT_GID, and PT_CREV, to monitor the real-time behavior of neighboring nodes and to manage route revocation. Trust evaluation is performed using packet-forwarding ratios, and false positives are detected. Additionally, the protocol checks each node's residual energy before forwarding data to the next node. To ensure data confidentiality, elliptic curve cryptography (ECC) is employed, providing robust encryption while reducing resource consumption. ECC is particularly beneficial for MANET devices with limited resources, as it offers strong security with lower overhead. Simulations conducted using NS2 software demonstrate that the proposed model outperforms the traditional AODV protocol in terms of network lifetime, packet delivery ratio, throughput, and delay, particularly under conditions of node mobility and varying node density. Overall, the proposed protocol offers a more robust, scalable, and secure solution for MANET environments compared to existing protocols.

移动自组织无线网络（manet）是分散的，缺乏固定的基础设施，这使得移动节点之间的动态和灵活通信成为可能。然而，这些网络面临着诸如有限的能源资源、频繁的拓扑变化以及节点不当行为导致的性能下降等挑战。像AODV这样的现有协议有很大的局限性，包括缺乏能量意识、无法检测恶意行为以及缺乏安全传输机制。这些弱点导致能量的迅速消耗和对攻击的脆弱性增加。为了解决这些问题，本文提出了一种新的能量感知的不可观察路由协议。新协议引入了自定义数据包类型，如PT_NID、PT_GID和PT_CREV，以监控邻近节点的实时行为并管理路由撤销。信任评估使用包转发比率执行，并检测假阳性。此外，在将数据转发到下一个节点之前，协议会检查每个节点的剩余能量。为了保证数据的机密性，采用了椭圆曲线加密（ECC），在提供鲁棒加密的同时减少了资源的消耗。ECC对于资源有限的MANET设备特别有利，因为它以较低的开销提供了强大的安全性。利用NS2软件进行的仿真表明，该模型在网络生存期、数据包投递率、吞吐量和延迟方面优于传统的AODV协议，特别是在节点移动和节点密度变化的条件下。总的来说，与现有协议相比，所提出的协议为MANET环境提供了更强大、可扩展和安全的解决方案。

{"title":"EAURP: An energy-efficient and trust-aware unobservable routing protocol for secure mobile Ad Hoc networks","authors":"A. Chandra , A.S.N. Chakravarthy","doi":"10.1016/j.suscom.2025.101285","DOIUrl":"10.1016/j.suscom.2025.101285","url":null,"abstract":"<div><div>Mobile ad hoc wireless networks (MANETs) are decentralized, lacking fixed infrastructure, which enables dynamic and flexible communication between mobile nodes. However, these networks face challenges such as limited energy resources, frequent topology changes, and performance degradation caused by node misbehavior. Existing protocols like AODV have significant limitations, including a lack of energy awareness, an inability to detect malicious behavior, and the absence of secure transmission mechanisms. These weaknesses lead to rapid energy depletion and increased vulnerability to attacks. To address these issues, this paper proposes a novel energy-aware unobservable routing protocol. The new protocol introduces custom packet types, such as PT_NID, PT_GID, and PT_CREV, to monitor the real-time behavior of neighboring nodes and to manage route revocation. Trust evaluation is performed using packet-forwarding ratios, and false positives are detected. Additionally, the protocol checks each node's residual energy before forwarding data to the next node. To ensure data confidentiality, elliptic curve cryptography (ECC) is employed, providing robust encryption while reducing resource consumption. ECC is particularly beneficial for MANET devices with limited resources, as it offers strong security with lower overhead. Simulations conducted using NS2 software demonstrate that the proposed model outperforms the traditional AODV protocol in terms of network lifetime, packet delivery ratio, throughput, and delay, particularly under conditions of node mobility and varying node density. Overall, the proposed protocol offers a more robust, scalable, and secure solution for MANET environments compared to existing protocols.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"49 ","pages":"Article 101285"},"PeriodicalIF":5.7,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145840587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Explainable and counterfactual lasso regression for resilient micro gas turbine power prediction in smart grids 智能电网弹性微燃气轮机功率预测的可解释与反事实套索回归

IF 5.7 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-12-15 DOI: 10.1016/j.suscom.2025.101284

Sheikh Muhammad Saqib , Muhammad Amir khan , Tariq Shahzad , Muhammad Usman Tariq , Tehseen Mazhar , Habib Hamam

Accurate prediction of electrical power output from micro gas turbines is essential for optimizing performance in microgrids and distributed power systems. This study introduces a novel and interpretable machine learning framework using Lasso regression applied to a newly published dataset titled Micro Gas Turbine Electrical Energy Prediction, available on Kaggle. The dataset captures time-series relationships between input control voltage and electrical power output, enabling effective modeling of micro turbine behavior. The proposed model relies on only two features, input voltage and time, ensuring computational efficiency while maintaining predictive performance. To support decision-making and model transparency, the framework incorporates Explainable AI (XAI) techniques such as SHAP and LIME, which reveal the influence of input features on predictions. Additionally, counterfactual analysis is integrated to explore how changes in inputs affect predicted outcomes. This allows users to define a minimum and maximum range for desired power outputs, providing actionable insight. The approach demonstrates high accuracy, with over 87 % of predictions falling into the low or category. By enabling interpretable and resource-efficient forecasting of local energy generation, the proposed framework contributes to the development of resilient and sustainable smart grid infrastructures. Most importantly, the proposed system is highly relevant for smart grid and microgrid operations, where transparent, accurate, and adaptive prediction of local generation units like micro gas turbines plays a critical role in maintaining system stability, load balancing, and energy efficiency.

准确预测微型燃气轮机的输出功率对于优化微电网和分布式电力系统的性能至关重要。本研究引入了一种新颖且可解释的机器学习框架，将Lasso回归应用于Kaggle上新发布的名为“微型燃气轮机电能预测”的数据集。该数据集捕获输入控制电压和电力输出之间的时间序列关系，从而实现对微型涡轮机行为的有效建模。该模型仅依赖于输入电压和时间两个特征，在保持预测性能的同时保证了计算效率。为了支持决策和模型透明度，该框架结合了可解释的人工智能（XAI）技术，如SHAP和LIME，这些技术揭示了输入特征对预测的影响。此外，反事实分析被整合以探索输入的变化如何影响预测结果。这允许用户定义所需功率输出的最小和最大范围，提供可操作的见解。该方法显示出很高的准确性，超过87% %的预测属于低或类别。通过实现可解释和资源高效的本地能源发电预测，拟议的框架有助于弹性和可持续智能电网基础设施的发展。最重要的是，所提出的系统与智能电网和微电网运行高度相关，其中微型燃气轮机等本地发电机组的透明、准确和自适应预测在维持系统稳定性、负载平衡和能源效率方面发挥着关键作用。

{"title":"Explainable and counterfactual lasso regression for resilient micro gas turbine power prediction in smart grids","authors":"Sheikh Muhammad Saqib , Muhammad Amir khan , Tariq Shahzad , Muhammad Usman Tariq , Tehseen Mazhar , Habib Hamam","doi":"10.1016/j.suscom.2025.101284","DOIUrl":"10.1016/j.suscom.2025.101284","url":null,"abstract":"<div><div>Accurate prediction of electrical power output from micro gas turbines is essential for optimizing performance in microgrids and distributed power systems. This study introduces a novel and interpretable machine learning framework using Lasso regression applied to a newly published dataset titled Micro Gas Turbine Electrical Energy Prediction, available on Kaggle. The dataset captures time-series relationships between input control voltage and electrical power output, enabling effective modeling of micro turbine behavior. The proposed model relies on only two features, input voltage and time, ensuring computational efficiency while maintaining predictive performance. To support decision-making and model transparency, the framework incorporates Explainable AI (XAI) techniques such as SHAP and LIME, which reveal the influence of input features on predictions. Additionally, counterfactual analysis is integrated to explore how changes in inputs affect predicted outcomes. This allows users to define a minimum and maximum range for desired power outputs, providing actionable insight. The approach demonstrates high accuracy, with over 87 % of predictions falling into the low or category. By enabling interpretable and resource-efficient forecasting of local energy generation, the proposed framework contributes to the development of resilient and sustainable smart grid infrastructures. Most importantly, the proposed system is highly relevant for smart grid and microgrid operations, where transparent, accurate, and adaptive prediction of local generation units like micro gas turbines plays a critical role in maintaining system stability, load balancing, and energy efficiency.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"49 ","pages":"Article 101284"},"PeriodicalIF":5.7,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145797833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Intelligent decision-making in smart grids using VANET and deep learning-based big data analysis 基于VANET和基于深度学习的大数据分析的智能电网智能决策

IF 5.7 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-12-14 DOI: 10.1016/j.suscom.2025.101283

Feng Xie, Zheng Tan, Ying Zhang, Shao-lin Wang, Zheng Cao, Cai-yue Yang

The increasing adoption of Electric Vehicles (EVs) and Renewable Energy (RE) sources in modern power systems presents challenges in maintaining grid stability, peak load management, and operational efficiency. This research developed an intelligent decision-making framework for VANET-enabled Smart Grids (SG) through Deep Learning (DL)-based big data analysis. A comprehensive framework is proposed that integrates Vehicle-to-Grid (V2G) optimization with a novel DL model, Emperor Penguins Colony-tuned Deep Belief with Attention-based Long Short-Term Memory (EPC-DB-AttLSTM). The framework gathers smart grid EV and renewable data and preprocessed it using data cleaning techniques such as K-Nearest Neighbour (kNN) imputation and normalization techniques like min-max normalization. Deep Belief (DB) Networks detects anomalies in grid operations, AttLSTM captures critical temporal patterns, Decision-making was enhanced through EPCO, EPC-DB-AttLSTM enables accurate forecasting and intelligent decisions which allocated EVs to charging stations efficiently, balanced load across the network, and maximized RE utilization. The attention mechanism highlights critical temporal patterns in EV load and grid data, improving prediction accuracy for intelligent decision-making. VANET communication enabled data exchange among EVs, charging stations, and grid controllers, supporting dynamic and scalable decision-making. The experiment was implemented using Python 3.10. The results demonstrated that the proposed framework achieved R² of 99.7, RMSE of 12.36, MAPE of 8.52, MSE of 1875.42, and MAE of 10.86. By integrating DL, big data analytics, and optimization-based decision-making, this framework provides a responsive, intelligent, and scalable SG solution, capable of accommodating high EV penetration and variable RE generation while optimizing operational strategies and ensuring sustainable energy management.

电动汽车（ev）和可再生能源（RE）在现代电力系统中的日益普及，给维持电网稳定性、峰值负荷管理和运行效率带来了挑战。本研究通过基于深度学习（DL）的大数据分析，为vanet智能电网（SG）开发了一个智能决策框架。提出了一种将车辆到电网（V2G）优化与一种新的深度学习模型——帝企鹅群体调谐深度信念与基于注意的长短期记忆（EPC-DB-AttLSTM）相结合的综合框架。该框架收集智能电网EV和可再生数据，并使用k -最近邻（kNN）插值等数据清洗技术和最小-最大归一化等归一化技术对其进行预处理。深度信念（DB）网络检测电网运行中的异常，AttLSTM捕获关键的时间模式，通过EPCO增强决策，EPC-DB-AttLSTM能够准确预测和智能决策，有效地将电动汽车分配到充电站，平衡整个网络的负载，并最大限度地利用可再生能源。注意机制突出了电动汽车负荷和电网数据的关键时间模式，提高了智能决策的预测精度。VANET通信实现了电动汽车、充电站和电网控制器之间的数据交换，支持动态和可扩展的决策。实验是使用Python 3.10实现的。结果表明，该框架的R²为99.7，RMSE为12.36，MAPE为8.52，MSE为1875.42，MAE为10.86。通过集成深度学习、大数据分析和基于优化的决策，该框架提供了一个响应迅速、智能且可扩展的SG解决方案，能够适应高电动汽车渗透率和可变可再生能源生成，同时优化运营策略并确保可持续能源管理。

{"title":"Intelligent decision-making in smart grids using VANET and deep learning-based big data analysis","authors":"Feng Xie, Zheng Tan, Ying Zhang, Shao-lin Wang, Zheng Cao, Cai-yue Yang","doi":"10.1016/j.suscom.2025.101283","DOIUrl":"10.1016/j.suscom.2025.101283","url":null,"abstract":"<div><div>The increasing adoption of Electric Vehicles (EVs) and Renewable Energy (RE) sources in modern power systems presents challenges in maintaining grid stability, peak load management, and operational efficiency. This research developed an intelligent decision-making framework for VANET-enabled Smart Grids (SG) through Deep Learning (DL)-based big data analysis. A comprehensive framework is proposed that integrates Vehicle-to-Grid (V2G) optimization with a novel DL model, Emperor Penguins Colony-tuned Deep Belief with Attention-based Long Short-Term Memory (EPC-DB-AttLSTM). The framework gathers smart grid EV and renewable data and preprocessed it using data cleaning techniques such as K-Nearest Neighbour (kNN) imputation and normalization techniques like min-max normalization. Deep Belief (DB) Networks detects anomalies in grid operations, AttLSTM captures critical temporal patterns, Decision-making was enhanced through EPCO, EPC-DB-AttLSTM enables accurate forecasting and intelligent decisions which allocated EVs to charging stations efficiently, balanced load across the network, and maximized RE utilization. The attention mechanism highlights critical temporal patterns in EV load and grid data, improving prediction accuracy for intelligent decision-making. VANET communication enabled data exchange among EVs, charging stations, and grid controllers, supporting dynamic and scalable decision-making. The experiment was implemented using Python 3.10. The results demonstrated that the proposed framework achieved R² of 99.7, RMSE of 12.36, MAPE of 8.52, MSE of 1875.42, and MAE of 10.86. By integrating DL, big data analytics, and optimization-based decision-making, this framework provides a responsive, intelligent, and scalable SG solution, capable of accommodating high EV penetration and variable RE generation while optimizing operational strategies and ensuring sustainable energy management.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"49 ","pages":"Article 101283"},"PeriodicalIF":5.7,"publicationDate":"2025-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145797831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

LFC of distributed power generation system under different cyberattacks utilizing mZOA based hFPD-PI+FP control strategy 基于mZOA的hFPD-PI+FP控制策略在不同网络攻击下的分布式发电系统LFC

IF 5.7 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-12-08 DOI: 10.1016/j.suscom.2025.101282

Surya Narayan Sahu , Rajendra Kumar Khadanga , Deepa Das , Yogendra Arya , Sidhartha Panda , Sasmita Padhy , Preeti Ranjan Sahu

The stability of electrical power load frequency control (LFC) system is threatened by frequency variations caused by violating the generation-demand balance and cyberattacks. This paper tackles the problem of LFC in a distributed power generation system (DPGS) that integrates energy storage and renewable energy sources. Using a modified Zebra Optimisation Algorithm (mZOA), a hybrid fuzzy PD-PI plus fuzzy P (hFPD-PI+FP) controller is suggested for LFC of DPGS under cyberattacks. Benchmark experiments validate the performance of the mZOA, showing that it performs better than the regular ZOA in terms of computation time and solution quality. According to simulation data, the mZOA based hFPD-PI+FP controller works better than the traditional PID controller at preserving frequency stability in the event of a cyberattack.

电力负荷频率控制系统的稳定性受到电力需求平衡和网络攻击等频率变化的威胁。本文研究了集成储能和可再生能源的分布式发电系统（DPGS）中的LFC问题。利用改进的斑马优化算法（mZOA），提出了一种模糊PD-PI+模糊P （hppd - pi +FP）混合控制器，用于网络攻击下DPGS的LFC。基准实验验证了mZOA的性能，表明它在计算时间和求解质量方面都优于常规的ZOA。仿真数据表明，与传统PID控制器相比，基于mZOA的hFPD-PI+FP控制器在网络攻击时能更好地保持频率稳定性。

引用次数: 0

Sustainable cybersecurity solutions for smart cities: Decentralized and resource-efficient architectures 智慧城市的可持续网络安全解决方案：分散和资源高效的架构

IF 5.7 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-12-06 DOI: 10.1016/j.suscom.2025.101280

R. Rajalakshmi , Bhuvan Unhelkar , Siva Shankar

The rapid growth of smart cities, powered by Internet of Things (IoT) technologies, demands robust, energy-efficient, and scalable cybersecurity solutions. As urban-scale systems increasingly depend on massive networks of sensors and edge devices, ensuring secure and sustainable communication becomes a critical challenge. This research presents a framework for Sustainable Cybersecurity Solutions, emphasizing Decentralized and Resource-Efficient Architectures for energy-optimized security in smart environments. Research proposes an Intelligent and Secure Edge-Enabled System (ISEC) model that integrates Green IoT, edge computing, and artificial intelligence (AI) to achieve secure, low-latency data transmission. It uses the smart city IoT and edge network dataset, applying Z-score normalization during preprocessing to standardize features and improve model performance, followed by Linear Discriminant Analysis (LDA) for feature extraction to maximize discriminative information and reduce dimensionality, thereby improving detection accuracy. The framework employs deep learning-based Termite Colony Optimizer-Driven Stacked Bidirectional Long Short-Term Memory (TCO-Stacked BiLSTM) to identify optimal routes and predict potential threats, enabling real-time threat detection and mitigation across the network. Edge computing decentralizes processing closer to IoT nodes, minimizing latency and reducing energy use. The ISEC model leverages this structure to avoid centralized bottlenecks, therefore embodying a resource-efficient architecture that balances security, computation, and power consumption. Low-powered sensors are supported through optimized routing protocols and lightweight security mechanisms, which reduce processing load and communication overhead. Experimental analysis shows the proposed TCO-Stacked BiLSTM model achieves accuracy, precision, recall, and F1-score ranging between 94 % and 98 %, along with reductions in energy consumption, latency, improvements in throughput, and significant enhancements in reliability, demonstrating efficient, low-latency, and resource-conscious performance for smart city IoT networks. These results confirm the efficiency and scalability of the model. Overall, the proposed solution provides a sustainable, secure, and resource-conscious framework, well-suited to the demands of modern smart cities and future urban digital infrastructures.

在物联网（IoT）技术的推动下，智慧城市的快速发展需要强大、节能和可扩展的网络安全解决方案。随着城市规模的系统越来越依赖于庞大的传感器和边缘设备网络，确保安全和可持续的通信成为一项关键挑战。本研究提出了一个可持续网络安全解决方案框架，强调在智能环境中实现能源优化安全的分散和资源高效架构。研究提出了一种智能安全的边缘启用系统（ISEC）模型，该模型集成了绿色物联网，边缘计算和人工智能（AI），以实现安全，低延迟的数据传输。利用智慧城市物联网和边缘网络数据集，在预处理过程中采用Z-score归一化来标准化特征，提高模型性能，然后通过线性判别分析（Linear Discriminant Analysis， LDA）进行特征提取，最大化判别信息，降低维数，从而提高检测精度。该框架采用基于深度学习的白蚁群优化器驱动的堆叠双向长短期记忆（TCO-Stacked BiLSTM）来识别最佳路由并预测潜在威胁，从而实现整个网络的实时威胁检测和缓解。边缘计算将处理分散到更靠近物联网节点的地方，最大限度地减少延迟并减少能源使用。ISEC模型利用这种结构来避免集中瓶颈，因此体现了一种资源高效的体系结构，可以平衡安全性、计算和功耗。通过优化的路由协议和轻量级安全机制支持低功耗传感器，从而减少处理负载和通信开销。实验分析表明，提出的TCO-Stacked BiLSTM模型实现了准确率、精密度、召回率和f1得分范围在94 %和98 %之间，同时降低了能耗、延迟、提高了吞吐量，并显著增强了可靠性，展示了智能城市物联网网络的高效、低延迟和资源意识性能。这些结果证实了该模型的有效性和可扩展性。总体而言，提出的解决方案提供了一个可持续、安全和资源意识的框架，非常适合现代智慧城市和未来城市数字基础设施的需求。

{"title":"Sustainable cybersecurity solutions for smart cities: Decentralized and resource-efficient architectures","authors":"R. Rajalakshmi , Bhuvan Unhelkar , Siva Shankar","doi":"10.1016/j.suscom.2025.101280","DOIUrl":"10.1016/j.suscom.2025.101280","url":null,"abstract":"<div><div>The rapid growth of smart cities, powered by Internet of Things (IoT) technologies, demands robust, energy-efficient, and scalable cybersecurity solutions. As urban-scale systems increasingly depend on massive networks of sensors and edge devices, ensuring secure and sustainable communication becomes a critical challenge. This research presents a framework for Sustainable Cybersecurity Solutions, emphasizing Decentralized and Resource-Efficient Architectures for energy-optimized security in smart environments. Research proposes an Intelligent and Secure Edge-Enabled System (ISEC) model that integrates Green IoT, edge computing, and artificial intelligence (AI) to achieve secure, low-latency data transmission. It uses the smart city IoT and edge network dataset, applying Z-score normalization during preprocessing to standardize features and improve model performance, followed by Linear Discriminant Analysis (LDA) for feature extraction to maximize discriminative information and reduce dimensionality, thereby improving detection accuracy. The framework employs deep learning-based Termite Colony Optimizer-Driven Stacked Bidirectional Long Short-Term Memory (TCO-Stacked BiLSTM) to identify optimal routes and predict potential threats, enabling real-time threat detection and mitigation across the network. Edge computing decentralizes processing closer to IoT nodes, minimizing latency and reducing energy use. The ISEC model leverages this structure to avoid centralized bottlenecks, therefore embodying a resource-efficient architecture that balances security, computation, and power consumption. Low-powered sensors are supported through optimized routing protocols and lightweight security mechanisms, which reduce processing load and communication overhead. Experimental analysis shows the proposed TCO-Stacked BiLSTM model achieves accuracy, precision, recall, and F1-score ranging between 94 % and 98 %, along with reductions in energy consumption, latency, improvements in throughput, and significant enhancements in reliability, demonstrating efficient, low-latency, and resource-conscious performance for smart city IoT networks. These results confirm the efficiency and scalability of the model. Overall, the proposed solution provides a sustainable, secure, and resource-conscious framework, well-suited to the demands of modern smart cities and future urban digital infrastructures.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"49 ","pages":"Article 101280"},"PeriodicalIF":5.7,"publicationDate":"2025-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145749257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cybersecurity meets carbon neutrality: Strategies for sustainable data center security operations 网络安全满足碳中和：可持续数据中心安全运营战略

IF 5.7 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-12-06 DOI: 10.1016/j.suscom.2025.101281

Thomas Samraj Lawrence , Martin Margala , Siva Shankar S , Prasun Chakrabarti , Nagarajan G

Data center security is enhanced with the rapid deployment of AI and ML in cybersecurity, yet energy use and carbon emissions have also increased with this development. In large-scale data center operations, this dual issue emphasizes the need for techniques that advance carbon neutrality while ensuring strong security. This research aims to design a sustainable cybersecurity framework that enhances computational performance while reducing environmental impact through energy-efficient modeling and optimization. This hybrid approach proposed an Oneclass Support Vector Based Bidirectional Snow Geese Algorithm (OSV-Bi-SGA). Carbon aware-cybersecurity traffic datasets are preprocessed through data cleaning, Z-score normalization, and categorical encoding to ensure robust input for modeling. Feature extraction is conducted using principal component analysis (PCA). The proposed OSV-Bi-SGA method is integrated with Bidirectional Long Short-Term Memory (BiLSTM), which captures temporal bidirectional dependencies in traffic sequences. Oneclass support vector machine (OSV) identifies anomalies when only normal class data is available. Snow Geese Algorithm (SGA) enhances parameter optimization, reducing energy cost while maintaining performance. The suggested OSV-Bi-SGA model achieved a high precision (99.42 %), recall (99.24 %), and F1-score (99.32 %), while reducing energy consumption and carbon footprint compared to baseline models. The research demonstrates that integrating evolutionary optimization with deep learning (DL), machine learning (ML) and anomaly detection can balance high-performance cybersecurity with reduced environmental impact. The OSV-Bi-SGA framework provides a promising pathway for sustainable and carbon-neutral data center security operations.

随着人工智能和机器学习在网络安全领域的快速部署，数据中心的安全性得到了增强，但能源使用和碳排放也随之增加。在大规模数据中心运营中，这一双重问题强调需要在确保强大安全性的同时推进碳中和的技术。本研究旨在设计一个可持续的网络安全框架，通过节能建模和优化来提高计算性能，同时减少对环境的影响。这种混合方法提出了一种基于单类支持向量的双向雪雁算法（OSV-Bi-SGA）。碳意识-网络安全流量数据集通过数据清洗，z分数标准化和分类编码进行预处理，以确保建模的鲁棒输入。使用主成分分析（PCA）进行特征提取。提出的OSV-Bi-SGA方法与双向长短期记忆（BiLSTM）相结合，用于捕获流量序列中的时间双向依赖关系。单类支持向量机（OSV）在只有正常类数据可用时识别异常。雪雁算法（SGA）增强了参数优化，在保持性能的同时降低了能源成本。与基线模型相比，OSV-Bi-SGA模型具有较高的精度（99.42 %）、召回率（99.24 %）和f1得分（99.32 %），同时降低了能耗和碳足迹。研究表明，将进化优化与深度学习（DL）、机器学习（ML）和异常检测相结合，可以在减少环境影响的同时平衡高性能网络安全。OSV-Bi-SGA框架为可持续和碳中性的数据中心安全运营提供了一条有希望的途径。

{"title":"Cybersecurity meets carbon neutrality: Strategies for sustainable data center security operations","authors":"Thomas Samraj Lawrence , Martin Margala , Siva Shankar S , Prasun Chakrabarti , Nagarajan G","doi":"10.1016/j.suscom.2025.101281","DOIUrl":"10.1016/j.suscom.2025.101281","url":null,"abstract":"<div><div>Data center security is enhanced with the rapid deployment of AI and ML in cybersecurity, yet energy use and carbon emissions have also increased with this development. In large-scale data center operations, this dual issue emphasizes the need for techniques that advance carbon neutrality while ensuring strong security. This research aims to design a sustainable cybersecurity framework that enhances computational performance while reducing environmental impact through energy-efficient modeling and optimization. This hybrid approach proposed an Oneclass Support Vector Based Bidirectional Snow Geese Algorithm (OSV-Bi-SGA). Carbon aware-cybersecurity traffic datasets are preprocessed through data cleaning, Z-score normalization, and categorical encoding to ensure robust input for modeling. Feature extraction is conducted using principal component analysis (PCA). The proposed <strong>OSV-Bi-SGA method is integrated with Bidirectional Long Short-Term Memory (BiLSTM), which</strong> captures temporal bidirectional dependencies in traffic sequences. <strong>Oneclass support vector machine (OSV) identifies</strong> anomalies when only normal class data is available. <strong>Snow Geese Algorithm (SGA)</strong> enhances parameter optimization, reducing energy cost while maintaining performance. The suggested OSV-Bi-SGA model achieved a high precision (99.42 %), recall (99.24 %), and F1-score (99.32 %), while reducing energy consumption and carbon footprint compared to baseline models. The research demonstrates that integrating evolutionary optimization with deep learning (DL), machine learning (ML) and anomaly detection can balance high-performance cybersecurity with reduced environmental impact. The OSV-Bi-SGA framework provides a promising pathway for sustainable and carbon-neutral data center security operations.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"49 ","pages":"Article 101281"},"PeriodicalIF":5.7,"publicationDate":"2025-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145749253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Challenges of IoT sensors in smart buildings ecosystems and integration of blockchain for enhanced security and efficiency 物联网传感器在智能建筑生态系统中的挑战和区块链的集成，以提高安全性和效率

IF 5.7 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-12-06 DOI: 10.1016/j.suscom.2025.101279

Syed Faisal Abbas Shah , Tehseen Mazhar , Muzammil Ahmad Khan , Shahab Ali Khan , Najeeb Ullah , Wasim Ahmad , Weiwei Jiang , Habib Hamam

Integrating Internet of Things (IoT) sensors into smart buildings has completely transformed the way to optimize and manage building management systems, from energy management to enhancing security systems. However, IoT sensors have several challenges in the context of smart buildings. The major challenge is that the vast quantity of data produced by the IoT sensors may outstrip the capabilities of current infrastructure, resulting in data storage, management, and analysis issues. Furthermore, the data generated by IoT sensors can also be unreliable and imprecise due to various environmental conditions, thereby impacting the performance of systems that rely on IoT technologies. Security is also a big challenge, as cyberattacks targeting IoT devices could endanger the confidentiality of building residents and premises. To address these challenges, adopting blockchain technology is a possible solution. Blockchain offers protection by using the decentralized ledger features for data collected from IoT sensors, as it guarantees permanent records are transparent and tamper-proof. This paper aims to highlight the different challenges faced by IoT sensors in smart buildings, and possible solutions are also provided, taking into consideration blockchain technologies. This review provides a detailed analysis of 104 works, synthesizing existing literature to evaluate the challenges of IoT sensors and how Blockchain-based approaches are applied to these challenges. This review addresses a specific gap: the absence of a building-specific, sensor-layer synthesis that systematically links smart-building IoT-sensor challenges to concrete blockchain design choices. Beyond surveying the field, we contribute a structured challenge mechanism mapping covering privacy/security, interoperability, scalability, real-time processing, energy, maintenance, localization, limited AI integration, and false positives to guide the design of secure and efficient building-management systems.

将物联网（IoT）传感器集成到智能建筑中，已经彻底改变了优化和管理建筑管理系统的方式，从能源管理到增强安全系统。然而，在智能建筑的背景下，物联网传感器面临着一些挑战。主要的挑战是，物联网传感器产生的大量数据可能超过当前基础设施的能力，从而导致数据存储、管理和分析问题。此外，由于各种环境条件，物联网传感器生成的数据也可能不可靠和不精确，从而影响依赖物联网技术的系统的性能。安全也是一个巨大的挑战，因为针对物联网设备的网络攻击可能会危及建筑物居民和房屋的机密性。为了应对这些挑战，采用区块链技术是一种可能的解决方案。区块链通过使用分散的分类账功能为从物联网传感器收集的数据提供保护，因为它保证永久记录是透明和防篡改的。本文旨在强调物联网传感器在智能建筑中面临的不同挑战，并在考虑区块链技术的情况下提供可能的解决方案。本文对104篇作品进行了详细分析，综合了现有文献，以评估物联网传感器的挑战，以及如何将基于区块链的方法应用于这些挑战。这篇综述解决了一个特定的空白：缺乏一个特定于建筑的传感器层综合，系统地将智能建筑物联网传感器挑战与具体的区块链设计选择联系起来。除了实地调查，我们还提供了一个结构化的挑战机制映射，涵盖隐私/安全、互操作性、可扩展性、实时处理、能源、维护、本地化、有限的人工智能集成和误报，以指导安全高效的建筑管理系统的设计。

{"title":"Challenges of IoT sensors in smart buildings ecosystems and integration of blockchain for enhanced security and efficiency","authors":"Syed Faisal Abbas Shah , Tehseen Mazhar , Muzammil Ahmad Khan , Shahab Ali Khan , Najeeb Ullah , Wasim Ahmad , Weiwei Jiang , Habib Hamam","doi":"10.1016/j.suscom.2025.101279","DOIUrl":"10.1016/j.suscom.2025.101279","url":null,"abstract":"<div><div>Integrating Internet of Things (IoT) sensors into smart buildings has completely transformed the way to optimize and manage building management systems, from energy management to enhancing security systems. However, IoT sensors have several challenges in the context of smart buildings. The major challenge is that the vast quantity of data produced by the IoT sensors may outstrip the capabilities of current infrastructure, resulting in data storage, management, and analysis issues. Furthermore, the data generated by IoT sensors can also be unreliable and imprecise due to various environmental conditions, thereby impacting the performance of systems that rely on IoT technologies. Security is also a big challenge, as cyberattacks targeting IoT devices could endanger the confidentiality of building residents and premises. To address these challenges, adopting blockchain technology is a possible solution. Blockchain offers protection by using the decentralized ledger features for data collected from IoT sensors, as it guarantees permanent records are transparent and tamper-proof. This paper aims to highlight the different challenges faced by IoT sensors in smart buildings, and possible solutions are also provided, taking into consideration blockchain technologies. This review provides a detailed analysis of 104 works, synthesizing existing literature to evaluate the challenges of IoT sensors and how Blockchain-based approaches are applied to these challenges. This review addresses a specific gap: the absence of a building-specific, sensor-layer synthesis that systematically links smart-building IoT-sensor challenges to concrete blockchain design choices. Beyond surveying the field, we contribute a structured challenge mechanism mapping covering privacy/security, interoperability, scalability, real-time processing, energy, maintenance, localization, limited AI integration, and false positives to guide the design of secure and efficient building-management systems.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"49 ","pages":"Article 101279"},"PeriodicalIF":5.7,"publicationDate":"2025-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145749256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A cooperative multi-objective evolutionary and deep reinforcement learning framework for sustainable distributed scheduling with preventive maintenance 具有预防性维护的可持续分布式调度的合作多目标进化深度强化学习框架

IF 5.7 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-12-04 DOI: 10.1016/j.suscom.2025.101266

Yanan Wang, Yuyan Han , Yuting Wang , Biao Zhang , Leilei Meng

Driven by global competition and energy efficiency demands, intelligent scheduling is critical for sustainable distributed manufacturing. This paper addresses the distributed group scheduling problem with preventive maintenance (DFGSP_PM) by establishing a threshold-based maintenance-triggered mathematical model. To effectively solve this problem, a novel Deep Q-network-based Cooperative Multi-objective Optimization Evolutionary algorithm (DQN-CMOEA) is proposed. The innovations lie in a DQN-driven adaptive strategy selection mechanism, a multi-population co-evolution framework for enhanced exploration, a maintenance-aware multi-phase energy-saving strategy for reducing idle-time energy waste, and a composite convergence-diversity indicator for promoting a well-distributed and high-quality Pareto front. Extensive experiments on 405 benchmark instances show that DQN-CMOEA significantly outperforms four state-of-the-art algorithms across multiple metrics, demonstrating its effectiveness and robustness in solving complex distributed scheduling problems.

在全球竞争和能源效率需求的驱动下，智能调度对可持续分布式制造至关重要。本文通过建立基于阈值的维护触发数学模型，解决了带有预防性维护的分布式组调度问题。为了有效解决这一问题，提出了一种基于深度q网络的协同多目标优化进化算法（DQN-CMOEA）。创新点包括dqn驱动的自适应策略选择机制、用于增强勘探的多种群协同进化框架、用于减少空闲时间能源浪费的维护感知多相节能策略以及用于促进分布良好、高质量的帕累托前沿的收敛多样性复合指标。在405个基准实例上的大量实验表明，DQN-CMOEA在多个指标上显著优于四种最先进的算法，证明了其在解决复杂分布式调度问题方面的有效性和鲁棒性。

{"title":"A cooperative multi-objective evolutionary and deep reinforcement learning framework for sustainable distributed scheduling with preventive maintenance","authors":"Yanan Wang, Yuyan Han , Yuting Wang , Biao Zhang , Leilei Meng","doi":"10.1016/j.suscom.2025.101266","DOIUrl":"10.1016/j.suscom.2025.101266","url":null,"abstract":"<div><div>Driven by global competition and energy efficiency demands, intelligent scheduling is critical for sustainable distributed manufacturing. This paper addresses the distributed group scheduling problem with preventive maintenance (DFGSP_PM) by establishing a threshold-based maintenance-triggered mathematical model. To effectively solve this problem, a novel Deep Q-network-based Cooperative Multi-objective Optimization Evolutionary algorithm (DQN-CMOEA) is proposed. The innovations lie in a DQN-driven adaptive strategy selection mechanism, a multi-population co-evolution framework for enhanced exploration, a maintenance-aware multi-phase energy-saving strategy for reducing idle-time energy waste, and a composite convergence-diversity indicator for promoting a well-distributed and high-quality Pareto front. Extensive experiments on 405 benchmark instances show that DQN-CMOEA significantly outperforms four state-of-the-art algorithms across multiple metrics, demonstrating its effectiveness and robustness in solving complex distributed scheduling problems.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"49 ","pages":"Article 101266"},"PeriodicalIF":5.7,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145749255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Continual learning-based regression testing for scalable VLSI verification across hierarchical design layers 跨分层设计层的可扩展VLSI验证的持续基于学习的回归测试

IF 5.7 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-12-01 DOI: 10.1016/j.suscom.2025.101259

Sindhu Nalla , G. Nagarajan

The high complexity and rapid evolution of Very Large-Scale Integration (VLSI) designs are pressing the limits of traditional regression testing especially in maintaining test relevance across design iterations. This paper introduces a Continual Learning-Based Regression Testing (CLRT) framework specifically designed for scalable VLSI verification across hierarchical abstraction levels such as logic, design, and chip. The framework overcomes the drawbacks of static test models through the stationary learning techniques, which are ingrained in the framework, and the ability to continuously learn and adjust the test strategy against every new design change and test results. To enforce the above property, our approach is based on a two-layer learning mechanism: the first layer is a supervised learning model with historical test outcomes for detecting regression-sensitive regions in the design space through the second one (an online continuous learning module) that can sequentially adapt to new data without catastrophic forgetting. This allows the system to remember learned test behavior and simultaneously adapt to changing design configurations. A hybrid feature selection mechanism is utilized for the extraction of the effective parameters, which should be extracted from design-level netlist, logic-level signals traces and fault logs at the chip bubbled status for a thorough cross-layer coverage. Experimental verification was performed on ITC-99 and Open Cores VLSI benchmark designs. The proposed CLRT framework achieved a remarkable reduction of 28.6 % in test redundancies and improvements of 35.2 % in fault detection accuracy when comparing to the traditional regression suites. Moreover, the system maintained a stable performance across variations of design, and this made it robust in dynamic testing conditions. The findings validate that CL models, if effectively integrated into rebase lining regression testing flows, can drastically augment the efficiency, flexibility, and scalability of the VLSI verification. Not only does this work offer a connecting point between machine learning and hierarchical VLSI testing, but it also paves the way for future self-improving test infrastructures in semiconductor design automation.

超大规模集成电路（VLSI）设计的高复杂性和快速发展正在挑战传统回归测试的极限，特别是在保持跨设计迭代的测试相关性方面。本文介绍了一个基于持续学习的回归测试（CLRT）框架，专为跨层次抽象级别（如逻辑、设计和芯片）的可扩展VLSI验证而设计。该框架通过在框架中根深蒂固的静态学习技术，以及根据每一个新的设计变化和测试结果不断学习和调整测试策略的能力，克服了静态测试模型的缺点。为了强化上述特性，我们的方法基于两层学习机制：第一层是具有历史测试结果的监督学习模型，用于检测设计空间中的回归敏感区域，第二层（在线连续学习模块）可以顺序适应新数据而不会发生灾难性遗忘。这允许系统记住学习的测试行为，同时适应不断变化的设计配置。利用混合特征选择机制提取有效参数，从芯片起泡状态下的设计级网表、逻辑级信号迹线和故障日志中提取有效参数，实现全面的跨层覆盖。在tc -99和Open Cores VLSI基准设计上进行了实验验证。与传统回归套件相比，所提出的CLRT框架的测试冗余度显著降低28.6 %，故障检测准确率显著提高35.2% %。此外，该系统在各种设计中都保持稳定的性能，这使其在动态测试条件下具有鲁棒性。研究结果验证了CL模型，如果有效地集成到rebase lining回归测试流程中，可以极大地提高VLSI验证的效率、灵活性和可扩展性。这项工作不仅提供了机器学习和分层VLSI测试之间的连接点，而且还为半导体设计自动化中未来自我改进的测试基础设施铺平了道路。

{"title":"Continual learning-based regression testing for scalable VLSI verification across hierarchical design layers","authors":"Sindhu Nalla , G. Nagarajan","doi":"10.1016/j.suscom.2025.101259","DOIUrl":"10.1016/j.suscom.2025.101259","url":null,"abstract":"<div><div>The high complexity and rapid evolution of Very Large-Scale Integration (VLSI) designs are pressing the limits of traditional regression testing especially in maintaining test relevance across design iterations. This paper introduces a Continual Learning-Based Regression Testing (CLRT) framework specifically designed for scalable VLSI verification across hierarchical abstraction levels such as logic, design, and chip. The framework overcomes the drawbacks of static test models through the stationary learning techniques, which are ingrained in the framework, and the ability to continuously learn and adjust the test strategy against every new design change and test results. To enforce the above property, our approach is based on a two-layer learning mechanism: the first layer is a supervised learning model with historical test outcomes for detecting regression-sensitive regions in the design space through the second one (an online continuous learning module) that can sequentially adapt to new data without catastrophic forgetting. This allows the system to remember learned test behavior and simultaneously adapt to changing design configurations. A hybrid feature selection mechanism is utilized for the extraction of the effective parameters, which should be extracted from design-level netlist, logic-level signals traces and fault logs at the chip bubbled status for a thorough cross-layer coverage. Experimental verification was performed on ITC-99 and Open Cores VLSI benchmark designs. The proposed CLRT framework achieved a remarkable reduction of 28.6 % in test redundancies and improvements of 35.2 % in fault detection accuracy when comparing to the traditional regression suites. Moreover, the system maintained a stable performance across variations of design, and this made it robust in dynamic testing conditions. The findings validatethat CL models, if effectively integrated into rebase lining regression testing flows, can drastically augment the efficiency, flexibility, and scalability of the VLSI verification. Not only does this work offer a connecting point between machine learning and hierarchical VLSI testing, but it also paves the way for future self-improving test infrastructures in semiconductor design automation.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"48 ","pages":"Article 101259"},"PeriodicalIF":5.7,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145614740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design and performance assessment of a green hydrogen and renewable integrated hybrid industrial microgrid with advanced control strategies considering uncertainties of renewable energy 考虑可再生能源不确定性的绿色氢能与可再生能源集成混合工业微电网设计与性能评价

IF 5.7 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-12-01 DOI: 10.1016/j.suscom.2025.101267

Javed Khan Bhutto , Arvind Kumar , Sarfaraz Kamangar , Amir Ibrahim Ali Arabi , Hadi Hakami

Hybrid industrial microgrids (HIMG) are emerging as a key enabler for decarbonizing energy-intensive sectors through the integration of renewable energy and green hydrogen technologies. This paper introduces the design, control, and performance assessment of a hybrid hydrogen integrated industrial microgrid comprising 1-MWp solar photovoltaic (PV) and 1.6-MW wind generator, a 650-kW proton exchange membrane fuel cell (PEMFC), a 3-MW battery energy storage system (BESS), and a 5-MW diesel generator supplying an electrolyzer and diverse industrial loads. The PV array operates at maximum power point tracking in grid-following mode, while the BESS and wind generator operate in grid-forming mode using droop control. To guarantee the steady operation of the HIMG, control methodologies for distributed generation and system-level control techniques for bidirectional interlinking converters (BIC) are developed. Resynchronization and planned islanding strategies are proposed to ensure seamless transitions between grid-connected and islanded operation. The system’s resynchronization performance is further evaluated by introducing intentional time delays into phase-locked loop measurements, demonstrating increasing oscillatory behavior and slower dynamic response at higher delays, while low-latency conditions enable fast and well-damped frequency recovery. The performance of the proposed controller is validated through detailed MATLAB/Simulink simulations under diverse operating scenarios, including islanding, grid reconnection, load disturbances, and severe three-phase fault conditions. Comprehensive simulation scenarios, including renewable uncertainties and load fluctuations, are evaluated against international performance standards. Frequency response analysis confirms the stability and robustness of the grid-forming control under dynamic conditions. Results demonstrate improved voltage and frequency regulation, reduced total harmonic distortion in voltage and current, and significant diesel usage reduction, confirming the proposed HIMG’s technical viability and sustainability benefits for industrial applications.

混合工业微电网（HIMG）正在成为通过整合可再生能源和绿色氢技术使能源密集型行业脱碳的关键推动者。本文介绍了由1 mwp太阳能光伏（PV）和1.6 mw风力发电机、650 kw质子交换膜燃料电池（PEMFC）、3 mw电池储能系统（BESS）和5 mw柴油发电机组成的混合氢集成工业微电网的设计、控制和性能评估。光伏阵列以最大功率点跟踪方式运行，采用电网跟随模式，而BESS和风力发电机采用下垂控制方式运行，采用电网形成模式。为了保证HIMG的稳定运行，研究了分布式发电的控制方法和双向互连变流器的系统级控制技术。提出了再同步和计划孤岛策略，以确保并网和孤岛运行之间的无缝过渡。通过在锁相环测量中引入有意的时间延迟，进一步评估了系统的再同步性能，显示出在高延迟下振荡行为增加，动态响应变慢，而低延迟条件下可以实现快速且阻尼良好的频率恢复。通过详细的MATLAB/Simulink仿真，验证了所提控制器在各种运行场景下的性能，包括孤岛、电网重连、负载扰动和严重三相故障条件。综合模拟情景，包括可再生能源的不确定性和负荷波动，根据国际性能标准进行评估。频率响应分析证实了动态条件下网格成形控制的稳定性和鲁棒性。结果表明，改进的电压和频率调节，降低了电压和电流的总谐波失真，并显著减少了柴油的使用，证实了所提出的HIMG在工业应用中的技术可行性和可持续性效益。

{"title":"Design and performance assessment of a green hydrogen and renewable integrated hybrid industrial microgrid with advanced control strategies considering uncertainties of renewable energy","authors":"Javed Khan Bhutto , Arvind Kumar , Sarfaraz Kamangar , Amir Ibrahim Ali Arabi , Hadi Hakami","doi":"10.1016/j.suscom.2025.101267","DOIUrl":"10.1016/j.suscom.2025.101267","url":null,"abstract":"<div><div>Hybrid industrial microgrids (HIMG) are emerging as a key enabler for decarbonizing energy-intensive sectors through the integration of renewable energy and green hydrogen technologies. This paper introduces the design, control, and performance assessment of a hybrid hydrogen integrated industrial microgrid comprising 1-MWp solar photovoltaic (PV) and 1.6-MW wind generator, a 650-kW proton exchange membrane fuel cell (PEMFC), a 3-MW battery energy storage system (BESS), and a 5-MW diesel generator supplying an electrolyzer and diverse industrial loads. The PV array operates at maximum power point tracking in grid-following mode, while the BESS and wind generator operate in grid-forming mode using droop control. To guarantee the steady operation of the HIMG, control methodologies for distributed generation and system-level control techniques for bidirectional interlinking converters (BIC) are developed. Resynchronization and planned islanding strategies are proposed to ensure seamless transitions between grid-connected and islanded operation. The system’s resynchronization performance is further evaluated by introducing intentional time delays into phase-locked loop measurements, demonstrating increasing oscillatory behavior and slower dynamic response at higher delays, while low-latency conditions enable fast and well-damped frequency recovery. The performance of the proposed controller is validated through detailed MATLAB/Simulink simulations under diverse operating scenarios, including islanding, grid reconnection, load disturbances, and severe three-phase fault conditions. Comprehensive simulation scenarios, including renewable uncertainties and load fluctuations, are evaluated against international performance standards. Frequency response analysis confirms the stability and robustness of the grid-forming control under dynamic conditions. Results demonstrate improved voltage and frequency regulation, reduced total harmonic distortion in voltage and current, and significant diesel usage reduction, confirming the proposed HIMG’s technical viability and sustainability benefits for industrial applications.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"48 ","pages":"Article 101267"},"PeriodicalIF":5.7,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145684118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0