Sustainable Computing-Informatics & Systems最新文献_第8页

Blockchain-enabled IoT framework with energy-efficient machine learning for scalable and secure smart cities 支持区块链的物联网框架，具有节能的机器学习，可扩展和安全的智能城市

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

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-21 DOI: 10.1016/j.suscom.2025.101212

Venkata Ramana Gupta Nallagattla , Amrita Rai , S. Thangam , G. Joel Sunny Deol , Abburi Srirama Kanaka Ratnam , J. Nageswara Rao , A. Santhi Mary Antony , K. Balasubramanian , Shamimul Qamar

In a rapidly urbanizing environment, cities have changed into complicated ecosystems requiring sophisticated technological solutions to resolve excessive traffic, energy utilization, waste management, and public safety issues. This study discusses a single architecture for IoT-enabled smart cities through the use of blockchain enabled security, energy efficient machine learning, real-time analytics, and decision-making to overcome scalability, interoperability, and security issues generally present in a smart infrastructure. The framework utilizes lightweight algorithm-based cost-effective computation, integration of heterogeneous IoT devices, real-time decision making, transparency, and involvement of stakeholders. The simulation findings show substantial advantages over traditional methods: a 35 % decrease in processing latency; a 25 % decrease in energy consumption; and a 29 % increase in an index for data security. Also, predictive analytics exhibited over 90 % identification accuracy across the different urban contexts, including traffic control for improved public safety, and environmental monitoring/management scenarios that ensured reliable forecasted events and appropriate resource allocation. The blockchain module demonstrated median transaction validation times of less than 2 ms to validate IoT data streams enabling real-time secure operations even under demanding environmental conditions. Also, we achieved resource allocation optimization with efficiencies that exceeded 85 % for designated priority supplies, including food, energy, medical resources, and reduced waste and improved disaster resilience. This model is adaptable across different urban settings and is a scalable, secure, and energy efficient framework for the next generation of smart cities contributing to sustainable urbanization and improved quality of urban life.

在快速城市化的环境中，城市已经变成了复杂的生态系统，需要复杂的技术解决方案来解决过度的交通、能源利用、废物管理和公共安全问题。本研究通过使用区块链支持的安全性、节能机器学习、实时分析和决策来克服智能基础设施中普遍存在的可扩展性、互操作性和安全性问题，讨论了支持物联网的智慧城市的单一架构。该框架利用基于轻量级算法的成本效益计算、异构物联网设备的集成、实时决策、透明度和利益相关者的参与。仿真结果显示了与传统方法相比的实质性优势：处理延迟降低了35% %；能源消耗降低25% %；数据安全指数提高了29% %。此外，预测分析在不同的城市环境中显示出超过90% %的识别准确率，包括改善公共安全的交通控制，以及确保可靠预测事件和适当资源分配的环境监测/管理场景。区块链模块演示了交易验证时间的中位数小于2 毫秒，以验证物联网数据流，即使在苛刻的环境条件下也能实现实时安全操作。此外，我们还实现了资源分配的优化，在指定的优先供应品（包括食品、能源和医疗资源）上的效率超过85% %，并减少了浪费，提高了抗灾能力。该模型适用于不同的城市环境，是下一代智慧城市的可扩展、安全和节能框架，有助于可持续城市化和提高城市生活质量。

{"title":"Blockchain-enabled IoT framework with energy-efficient machine learning for scalable and secure smart cities","authors":"Venkata Ramana Gupta Nallagattla , Amrita Rai , S. Thangam , G. Joel Sunny Deol , Abburi Srirama Kanaka Ratnam , J. Nageswara Rao , A. Santhi Mary Antony , K. Balasubramanian , Shamimul Qamar","doi":"10.1016/j.suscom.2025.101212","DOIUrl":"10.1016/j.suscom.2025.101212","url":null,"abstract":"<div><div>In a rapidly urbanizing environment, cities have changed into complicated ecosystems requiring sophisticated technological solutions to resolve excessive traffic, energy utilization, waste management, and public safety issues. This study discusses a single architecture for IoT-enabled smart cities through the use of blockchain enabled security, energy efficient machine learning, real-time analytics, and decision-making to overcome scalability, interoperability, and security issues generally present in a smart infrastructure. The framework utilizes lightweight algorithm-based cost-effective computation, integration of heterogeneous IoT devices, real-time decision making, transparency, and involvement of stakeholders. The simulation findings show substantial advantages over traditional methods: a 35 % decrease in processing latency; a 25 % decrease in energy consumption; and a 29 % increase in an index for data security. Also, predictive analytics exhibited over 90 % identification accuracy across the different urban contexts, including traffic control for improved public safety, and environmental monitoring/management scenarios that ensured reliable forecasted events and appropriate resource allocation. The blockchain module demonstrated median transaction validation times of less than 2 ms to validate IoT data streams enabling real-time secure operations even under demanding environmental conditions. Also, we achieved resource allocation optimization with efficiencies that exceeded 85 % for designated priority supplies, including food, energy, medical resources, and reduced waste and improved disaster resilience. This model is adaptable across different urban settings and is a scalable, secure, and energy efficient framework for the next generation of smart cities contributing to sustainable urbanization and improved quality of urban life.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"48 ","pages":"Article 101212"},"PeriodicalIF":5.7,"publicationDate":"2025-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158256","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

An efficient multi-objective task scheduling for Green cloud computing using hybrid GSCOA algorithm 基于混合GSCOA算法的绿色云计算多目标任务调度

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

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-16 DOI: 10.1016/j.suscom.2025.101209

Kata Vijay Kumar, Ganesh Reddy Karri

With the expansion of data centres in recent years, energy-related challenges have become worse. Green cloud computing (GCC) is a new computing paradigm designed to address cloud data centre energy consumption. Even with the advancements in GCC, large-scale green cloud data centres (GCDCs) continue to confront significant obstacles in lowering carbon emissions and energy consumption, particularly in the area of task scheduling. Ineffective task distribution can result in underutilized servers and overworked servers, wasting energy. Workload fluctuations make it difficult to manage resources effectively, which frequently results in energy spikes during periods of high demand. These dynamic demands are frequently not adequately satisfied by the current scheduling techniques since they might not take into consideration changing workload patterns. Therefore, in this work, an effective hybrid Greylag Sand Cat Swarm Optimization Algorithm (GSCOA) is introduced to schedule the task effectively in GCDC. This hybrid approach makes use of the Sand Cat Swarm Optimization Algorithm's (SCSOA) exploitation skills and the Greylag Goose Optimization algorithm's (GGOA) exploring capabilities. This combination makes it possible to schedule cloud user requirements to the cloud server efficiently by minimizing energy consumption. It helps the cloud server system emit less carbon dioxide, allowing for a more environmentally friendly atmosphere. Simulation results on two real-world workloads-NASA-IPSC and HPC2N, indicate that the proposed approach significantly outperforms existing scheduling methods by reducing energy consumption and improving overall system performance.

随着近年来数据中心的扩张，与能源相关的挑战变得更加严重。绿色云计算（GCC）是一种新的计算范式，旨在解决云数据中心的能源消耗问题。尽管海湾合作委员会取得了进展，但大型绿色云数据中心在降低碳排放和能源消耗方面继续面临重大障碍，特别是在任务调度领域。无效的任务分配可能导致服务器利用率不足和服务器过度工作，浪费能源。工作负载的波动使得难以有效地管理资源，这经常导致在高需求期间出现能量峰值。当前的调度技术往往不能充分满足这些动态需求，因为它们可能没有考虑到不断变化的工作负载模式。为此，本文引入了一种有效的混合灰沙猫群优化算法（GSCOA）来有效地调度GCDC中的任务。这种混合方法利用了Sand Cat Swarm Optimization Algorithm （SCSOA）的开发技能和Greylag Goose Optimization Algorithm （GGOA）的探索能力。这种组合可以通过最小化能耗来有效地将云用户需求安排到云服务器。它有助于云服务器系统排放更少的二氧化碳，从而营造更环保的氛围。在nasa - ipsc和HPC2N两个实际工作负载上的仿真结果表明，该方法通过降低能耗和提高系统整体性能，显著优于现有的调度方法。

{"title":"An efficient multi-objective task scheduling for Green cloud computing using hybrid GSCOA algorithm","authors":"Kata Vijay Kumar, Ganesh Reddy Karri","doi":"10.1016/j.suscom.2025.101209","DOIUrl":"10.1016/j.suscom.2025.101209","url":null,"abstract":"<div><div>With the expansion of data centres in recent years, energy-related challenges have become worse. Green cloud computing (GCC) is a new computing paradigm designed to address cloud data centre energy consumption. Even with the advancements in GCC, large-scale green cloud data centres (GCDCs) continue to confront significant obstacles in lowering carbon emissions and energy consumption, particularly in the area of task scheduling. Ineffective task distribution can result in underutilized servers and overworked servers, wasting energy. Workload fluctuations make it difficult to manage resources effectively, which frequently results in energy spikes during periods of high demand. These dynamic demands are frequently not adequately satisfied by the current scheduling techniques since they might not take into consideration changing workload patterns. Therefore, in this work, an effective hybrid Greylag Sand Cat Swarm Optimization Algorithm (GSCOA) is introduced to schedule the task effectively in GCDC. This hybrid approach makes use of the Sand Cat Swarm Optimization Algorithm's (SCSOA) exploitation skills and the Greylag Goose Optimization algorithm's (GGOA) exploring capabilities. This combination makes it possible to schedule cloud user requirements to the cloud server efficiently by minimizing energy consumption. It helps the cloud server system emit less carbon dioxide, allowing for a more environmentally friendly atmosphere. Simulation results on two real-world workloads-NASA-IPSC and HPC2N, indicate that the proposed approach significantly outperforms existing scheduling methods by reducing energy consumption and improving overall system performance.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"48 ","pages":"Article 101209"},"PeriodicalIF":5.7,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096417","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

MEDALS: A sustainable AI framework for energy-efficient routing in 5G vehicular networks 奖牌：5G车辆网络中节能路由的可持续人工智能框架

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

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-15 DOI: 10.1016/j.suscom.2025.101210

G. Balram , KDV Prasad , Kamalakar Ramineni , Rahul Divgan , K. Ashok , N.V. Phani Sai Kumar

Intelligent transportation systems require routing protocols that optimize both performance and environmental impact simultaneously in 5G-enabled Vehicular Ad Hoc Networks (VANETs). Existing solutions often treat sustainability as a secondary constraint, which limits their effectiveness in addressing climate change goals. This study presents MEDALS (Metaheuristic-Enhanced Deep Adaptive Learning System), a hybrid framework that integrates deep reinforcement learning with metaheuristic optimization to achieve both superior performance and environmental sustainability. The system introduces the Green Performance Index (GPI), the first comprehensive metric combining energy efficiency, carbon footprint, latency, and reliability. Through extensive evaluation using industry-standard simulators, MEDALS demonstrates statistically significant improvements: MEDALS achieves 96.8 % energy efficiency (+11.6 %), 0.73 ms latency (-91.6 %), 99.7 % reliability, and 42.3 % carbon reduction while scaling to 1000 + vehicles with linear computational complexity. This will allow its practical implementation in smart cities and towards fulfillment of the sustainable development goals. This complexity augmentation of 3.3x times in the network size handling is attributed to the hybrid intelligence architecture of the framework, the adaptive deep reinforcement learning with the dual metaheuristic optimisation in intelligent fusion mechanism, and the empirically quantified O(N log N) complexity.

智能交通系统需要在支持5g的车辆自组织网络（VANETs）中同时优化性能和环境影响的路由协议。现有的解决方案往往将可持续性视为次要制约因素，这限制了它们在解决气候变化目标方面的有效性。本研究提出了奖牌（元启发式增强型深度适应学习系统），这是一个混合框架，将深度强化学习与元启发式优化相结合，以实现卓越的性能和环境可持续性。该系统引入了绿色绩效指数（GPI），这是首个综合能源效率、碳足迹、延迟和可靠性的指标。通过使用行业标准模拟器进行广泛评估，奖牌显示了统计上显着的改进：奖牌实现了96.8% %的能源效率（+11.6 %），0.73 毫秒的延迟（-91.6 %），99.7 %的可靠性，以及42.3 %的碳减排，同时扩展到1000辆 + 车辆，具有线性计算复杂性。这将使其能够在智慧城市中实际实施，并实现可持续发展目标。在网络规模处理方面，这种3.3倍的复杂度提升归功于框架的混合智能架构、智能融合机制中具有双元启发式优化的自适应深度强化学习以及经验量化的O（N log N）复杂度。

{"title":"MEDALS: A sustainable AI framework for energy-efficient routing in 5G vehicular networks","authors":"G. Balram , KDV Prasad , Kamalakar Ramineni , Rahul Divgan , K. Ashok , N.V. Phani Sai Kumar","doi":"10.1016/j.suscom.2025.101210","DOIUrl":"10.1016/j.suscom.2025.101210","url":null,"abstract":"<div><div>Intelligent transportation systems require routing protocols that optimize both performance and environmental impact simultaneously in 5G-enabled Vehicular Ad Hoc Networks (VANETs). Existing solutions often treat sustainability as a secondary constraint, which limits their effectiveness in addressing climate change goals. This study presents MEDALS (Metaheuristic-Enhanced Deep Adaptive Learning System), a hybrid framework that integrates deep reinforcement learning with metaheuristic optimization to achieve both superior performance and environmental sustainability. The system introduces the Green Performance Index (GPI), the first comprehensive metric combining energy efficiency, carbon footprint, latency, and reliability. Through extensive evaluation using industry-standard simulators, MEDALS demonstrates statistically significant improvements: MEDALS achieves 96.8 % energy efficiency (+11.6 %), 0.73 ms latency (-91.6 %), 99.7 % reliability, and 42.3 % carbon reduction while scaling to 1000 + vehicles with linear computational complexity. This will allow its practical implementation in smart cities and towards fulfillment of the sustainable development goals. This complexity augmentation of 3.3x times in the network size handling is attributed to the hybrid intelligence architecture of the framework, the adaptive deep reinforcement learning with the dual metaheuristic optimisation in intelligent fusion mechanism, and the empirically quantified O(N log N) complexity.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"48 ","pages":"Article 101210"},"PeriodicalIF":5.7,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158338","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

Integrating blockchain and iot with advanced predictive modeling for energy efficient urban transportation systems 将区块链和物联网与高效节能城市交通系统的先进预测建模相结合

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

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-15 DOI: 10.1016/j.suscom.2025.101208

Jyotsnarani Tripathy , M. Kaliappan , Gnana Kousalya Chellathevar , J. Relin Francis Raj , Ravivarman Shanmugasundaram , Manjunathan Alagarsamy , S.Patricia Nancy , Ali Algahtani

In a world that is rapidly urbanising and EV-dependent, the energy efficiency and sustainability of transportation infrastructures is a daunting challenge. It introduces the Blockchain-Based IoT Urban Transport Optimizer (BIUTO), a new approach that combines IOT, blockchain and predictive modeling for traffic management, EV charging efficiency, and building energy consumption. The framework aims to circumvent major drawbacks of current centralized architectures, such as data breaches, scaling, and inability to dynamically manage nested urban systems. The technology leverages IoT for real-time collection, Machine Learning Models (LSTM, Gradient Boosted Decision Trees, or GBDT) for predictive analytics, and blockchain for secure and decentralized data storage. The traffic subsystem helped reduce peak congestion by 23 % via real-time traffic flow prediction, and the EV charging subsystem increased energy efficiency by 15 %. The building energy efficiency subsystem reported high RMSE values for heating and cooling loads. The blockchain layer made data secure and transparent, alleviating issues with centralized system malfunctions. This work brings to the table a single, scaling approach to sustainable city transport based on energy efficiency, which will also serve as part of the sustainability agenda worldwide. The flexibility of BIUTO to integrate multiple urban subsystems represents an enormous step forward towards smart, low-carbon cities. Future efforts will include scaling the blockchain latency and scaling up the model to include renewable energy.

在一个快速城市化和依赖电动汽车的世界，交通基础设施的能源效率和可持续性是一项艰巨的挑战。它引入了基于区块链的物联网城市交通优化器（BIUTO），这是一种将物联网，区块链和交通管理，电动汽车充电效率和建筑能耗预测建模相结合的新方法。该框架旨在规避当前集中式架构的主要缺点，例如数据泄露、扩展以及无法动态管理嵌套城市系统。该技术利用物联网进行实时收集，利用机器学习模型（LSTM、梯度增强决策树或GBDT）进行预测分析，利用区块链进行安全和分散的数据存储。交通子系统通过实时交通流预测，帮助高峰拥堵减少了23% %，电动汽车充电子系统提高了15% %的能源效率。建筑能效子系统报告了加热和冷却负荷的高RMSE值。区块链层使数据安全和透明，减轻了集中式系统故障的问题。这项工作为基于能源效率的可持续城市交通提供了一种单一的、可扩展的方法，这也将成为全球可持续发展议程的一部分。BIUTO集成多个城市子系统的灵活性代表着向智能低碳城市迈进了一大步。未来的努力将包括扩大区块链延迟和扩大模型以包括可再生能源。

{"title":"Integrating blockchain and iot with advanced predictive modeling for energy efficient urban transportation systems","authors":"Jyotsnarani Tripathy , M. Kaliappan , Gnana Kousalya Chellathevar , J. Relin Francis Raj , Ravivarman Shanmugasundaram , Manjunathan Alagarsamy , S.Patricia Nancy , Ali Algahtani","doi":"10.1016/j.suscom.2025.101208","DOIUrl":"10.1016/j.suscom.2025.101208","url":null,"abstract":"<div><div>In a world that is rapidly urbanising and EV-dependent, the energy efficiency and sustainability of transportation infrastructures is a daunting challenge. It introduces the Blockchain-Based IoT Urban Transport Optimizer (BIUTO), a new approach that combines IOT, blockchain and predictive modeling for traffic management, EV charging efficiency, and building energy consumption. The framework aims to circumvent major drawbacks of current centralized architectures, such as data breaches, scaling, and inability to dynamically manage nested urban systems. The technology leverages IoT for real-time collection, Machine Learning Models (LSTM, Gradient Boosted Decision Trees, or GBDT) for predictive analytics, and blockchain for secure and decentralized data storage. The traffic subsystem helped reduce peak congestion by 23 % via real-time traffic flow prediction, and the EV charging subsystem increased energy efficiency by 15 %. The building energy efficiency subsystem reported high RMSE values for heating and cooling loads. The blockchain layer made data secure and transparent, alleviating issues with centralized system malfunctions. This work brings to the table a single, scaling approach to sustainable city transport based on energy efficiency, which will also serve as part of the sustainability agenda worldwide. The flexibility of BIUTO to integrate multiple urban subsystems represents an enormous step forward towards smart, low-carbon cities. Future efforts will include scaling the blockchain latency and scaling up the model to include renewable energy.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"48 ","pages":"Article 101208"},"PeriodicalIF":5.7,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220315","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

Energy-efficient smart grid operations through dynamic digital twin models and deep learning 通过动态数字孪生模型和深度学习实现节能智能电网运行

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

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-13 DOI: 10.1016/j.suscom.2025.101200

Guilin He, Min Lei, Lei Han, Peifa Shan, Ruipeng Chen

Adopting the dynamic digital twin (DDT) model in smart grid distribution networks is a revolutionary breakthrough toward advanced dynamic energy management and control. However, even the most advanced systems fail to describe static architectural configuration adequately or they do not offer sufficient automation in this process, they are unable to handle dynamic interactions or topological hierarchy. To overcome such restrictions, this research presents a new framework for building DDT models based on Graph Neural Networks (GNNs). GNNs outperform other deep learning models when it comes to modeling graph-structured data which has application in modeling nodes and edges of smart grids. The adopted model expands the critical technical parameters' achievements and indicates a high Voltage Regulation Efficiency of 92 % and Network Efficiency belonging to 95 %; therefore, the distribution of power and operation reliability is considered optimal. The advantage of these findings is also echoed by the Voltage Profile Deviation of 0.015 p.u. and the Power Loss Reduction of 18.3 % which suggest that the proposed method offers better voltage profile stability and less energy losses than existing static models. The usefulness and applicability of the framework can be shown by performing experiments in MATLAB Simulink and Python-based libraries such as PyTorch Geometric. This study provides a novel approach to address issues in applied research and provides the basis for further advancements in realistic digital twin applications concerning smart grids.

在智能电网配电网中采用动态数字孪生（DDT）模型是实现先进动态能源管理与控制的革命性突破。然而，即使是最先进的系统也不能充分描述静态体系结构配置，或者它们不能在这个过程中提供足够的自动化，它们不能处理动态交互或拓扑层次结构。为了克服这些限制，本研究提出了一种基于图神经网络（gnn）构建DDT模型的新框架。当涉及到对图结构数据的建模时，gnn优于其他深度学习模型，这在智能电网的节点和边缘建模中有应用。所采用的模型扩展了关键技术参数的成果，表明稳压效率为92 %，网络效率为95 %；因此，功率分配和运行可靠性被认为是最优的。电压分布偏差0.015 p.u.和功率损耗降低18.3 %也反映了这些发现的优势，这表明所提出的方法比现有的静态模型具有更好的电压分布稳定性和更少的能量损失。通过在MATLAB Simulink和基于python的库（如PyTorch Geometric）中进行实验，可以证明该框架的实用性和适用性。该研究为解决应用研究中的问题提供了一种新的方法，并为智能电网中现实数字孪生应用的进一步发展提供了基础。

{"title":"Energy-efficient smart grid operations through dynamic digital twin models and deep learning","authors":"Guilin He, Min Lei, Lei Han, Peifa Shan, Ruipeng Chen","doi":"10.1016/j.suscom.2025.101200","DOIUrl":"10.1016/j.suscom.2025.101200","url":null,"abstract":"<div><div>Adopting the dynamic digital twin (DDT) model in smart grid distribution networks is a revolutionary breakthrough toward advanced dynamic energy management and control. However, even the most advanced systems fail to describe static architectural configuration adequately or they do not offer sufficient automation in this process, they are unable to handle dynamic interactions or topological hierarchy. To overcome such restrictions, this research presents a new framework for building DDT models based on Graph Neural Networks (GNNs). GNNs outperform other deep learning models when it comes to modeling graph-structured data which has application in modeling nodes and edges of smart grids. The adopted model expands the critical technical parameters' achievements and indicates a high Voltage Regulation Efficiency of 92 % and Network Efficiency belonging to 95 %; therefore, the distribution of power and operation reliability is considered optimal. The advantage of these findings is also echoed by the Voltage Profile Deviation of 0.015 p.u. and the Power Loss Reduction of 18.3 % which suggest that the proposed method offers better voltage profile stability and less energy losses than existing static models. The usefulness and applicability of the framework can be shown by performing experiments in MATLAB Simulink and Python-based libraries such as PyTorch Geometric. This study provides a novel approach to address issues in applied research and provides the basis for further advancements in realistic digital twin applications concerning smart grids.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"48 ","pages":"Article 101200"},"PeriodicalIF":5.7,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096416","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

Energy-efficient communication in WSNs using ABCP: An Aurora and quantum tunneling approach 基于ABCP的无线传感器网络节能通信：极光和量子隧道方法

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

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-12 DOI: 10.1016/j.suscom.2025.101202

Salim El khediri , Pascal Lorenz

Cluster-based routing has been effective for facing the unique problems of Wireless Sensor Networks such as handling energy consumption and forwarding data in large, limited resource environments. Based on how the Aurora Borealis changes over time, this paper proposes the Aurora-Based Clustering Protocol which relies on virtual electrical drift and quantum tunneling to select flexible clusters and their heads. According to ABCP, a sensor node is represented by a charged particle and its virtual charge is measured by considering remaining energy and nearby data amounts. Nodes in the network are linked by streamlines created with magnetic-inspired methods and cluster heads are selected randomly using a fitness model that aims for both balance and central locations. It offers support for changing network arrangements and arranges paths so that communication is efficient wherever and whenever users move. ABCP was tested by running multiple simulations with a network of 300 nodes which reflects how a WSN might be used in real life. Against standard approaches such as LEACH, BeeCluster, iABC and PSO-based schemes, ABCP saves up to 28.7% more energy and adds at least 17.4% to the network’s lifetime under varying and densely packed node conditions.

基于集群的路由在面对无线传感器网络的独特问题时是有效的，例如在大型、有限的资源环境中处理能量消耗和转发数据。根据北极光随时间的变化规律，提出了基于虚拟电漂移和量子隧道的基于北极光的聚类协议，该协议可以选择柔性簇及其簇头。根据ABCP，传感器节点由带电粒子表示，通过考虑剩余能量和附近数据量来测量其虚电荷。网络中的节点通过以磁力为灵感的方法创建的流线连接起来，并且使用旨在平衡和中心位置的健身模型随机选择簇头。它支持更改网络安排和安排路径，以便无论何时何地用户移动，通信都是有效的。ABCP通过在300个节点的网络上运行多个模拟来测试，这反映了WSN在现实生活中的使用情况。与LEACH、BeeCluster、iABC和基于pso的标准方法相比，在不同和密集的节点条件下，ABCP节省了高达28.7%的能量，并至少增加了17.4%的网络寿命。

{"title":"Energy-efficient communication in WSNs using ABCP: An Aurora and quantum tunneling approach","authors":"Salim El khediri , Pascal Lorenz","doi":"10.1016/j.suscom.2025.101202","DOIUrl":"10.1016/j.suscom.2025.101202","url":null,"abstract":"<div><div>Cluster-based routing has been effective for facing the unique problems of Wireless Sensor Networks such as handling energy consumption and forwarding data in large, limited resource environments. Based on how the Aurora Borealis changes over time, this paper proposes the Aurora-Based Clustering Protocol which relies on virtual electrical drift and quantum tunneling to select flexible clusters and their heads. According to ABCP, a sensor node is represented by a charged particle and its virtual charge is measured by considering remaining energy and nearby data amounts. Nodes in the network are linked by streamlines created with magnetic-inspired methods and cluster heads are selected randomly using a fitness model that aims for both balance and central locations. It offers support for changing network arrangements and arranges paths so that communication is efficient wherever and whenever users move. ABCP was tested by running multiple simulations with a network of 300 nodes which reflects how a WSN might be used in real life. Against standard approaches such as LEACH, BeeCluster, iABC and PSO-based schemes, ABCP saves up to 28.7% more energy and adds at least 17.4% to the network’s lifetime under varying and densely packed node conditions.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"48 ","pages":"Article 101202"},"PeriodicalIF":5.7,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096418","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

Automated deep learning and Internet of Things framework for building energy management: A university case study 自动化深度学习和物联网框架的建筑能源管理：一个大学案例研究

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

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-10 DOI: 10.1016/j.suscom.2025.101198

Deepshikha Shrivastava , Prerna Goswami

Monitoring energy consumption in buildings presents significant opportunities, especially in developing economies like India. However, current solutions often overlook cost-effective, small-scale, accurate, and open-source data-driven methodologies. Research in this area is often hindered by concerns related to security and privacy, high investment costs, and unpredictable returns. To address these challenges, we developed an automated hybrid deep learning and Internet of Things (DL-IoT) building energy management system (BEMS) aimed at conserving energy. The DL-IoT combines deep learning techniques with fuzzy logic to effectively manage uncertainty and noise in electrical properties. Our DL-IoT regression model demonstrated low mean absolute error and mean squared error, achieving a coefficient of determination of 0.99 for out-of-sample energy consumption predictions. We extracted twenty-seven electricity usage variables from raw data to train the model. Experimental results revealed a linear relationship between these characteristics and energy use. The proposed model successfully predicted features that could contribute to energy savings, such as Power Factor and Power in the Y Phase. Specifically, it estimated that a one-unit increase in Power in the Y Phase and Power Factor would result in a reduction in energy consumption. The findings of the experiment indicated that the model captured the variability of the data better than other models. The results demonstrated the superiority of the proposed model over other mainstream existing models. Through the results of this paper, a more efficient energy data management and consumption plan can be established.

监测建筑能耗带来了巨大的机遇，尤其是在印度这样的发展中经济体。然而，当前的解决方案往往忽略了成本效益高、规模小、准确和开源的数据驱动方法。这一领域的研究经常受到安全和隐私、高投资成本和不可预测回报等问题的阻碍。为了应对这些挑战，我们开发了一种自动化的混合深度学习和物联网（DL-IoT）建筑能源管理系统（BEMS），旨在节约能源。DL-IoT将深度学习技术与模糊逻辑相结合，有效管理电性能中的不确定性和噪声。我们的DL-IoT回归模型显示出较低的平均绝对误差和均方误差，样本外能耗预测的决定系数为0.99。我们从原始数据中提取了27个用电量变量来训练模型。实验结果表明，这些特征与能源使用之间存在线性关系。所提出的模型成功地预测了有助于节能的特征，如功率因数和Y阶段的功率。具体来说，它估计在Y相和功率因数中增加一个单位的功率将导致能耗的减少。实验结果表明，该模型比其他模型更好地捕捉了数据的可变性。结果表明，该模型优于其他主流模型。通过本文的研究结果，可以建立一个更有效的能源数据管理和消费计划。

{"title":"Automated deep learning and Internet of Things framework for building energy management: A university case study","authors":"Deepshikha Shrivastava , Prerna Goswami","doi":"10.1016/j.suscom.2025.101198","DOIUrl":"10.1016/j.suscom.2025.101198","url":null,"abstract":"<div><div>Monitoring energy consumption in buildings presents significant opportunities, especially in developing economies like India. However, current solutions often overlook cost-effective, small-scale, accurate, and open-source data-driven methodologies. Research in this area is often hindered by concerns related to security and privacy, high investment costs, and unpredictable returns. To address these challenges, we developed an automated hybrid deep learning and Internet of Things (DL-IoT) building energy management system (BEMS) aimed at conserving energy. The DL-IoT combines deep learning techniques with fuzzy logic to effectively manage uncertainty and noise in electrical properties. Our DL-IoT regression model demonstrated low mean absolute error and mean squared error, achieving a coefficient of determination of 0.99 for out-of-sample energy consumption predictions. We extracted twenty-seven electricity usage variables from raw data to train the model. Experimental results revealed a linear relationship between these characteristics and energy use. The proposed model successfully predicted features that could contribute to energy savings, such as Power Factor and Power in the Y Phase. Specifically, it estimated that a one-unit increase in Power in the Y Phase and Power Factor would result in a reduction in energy consumption. The findings of the experiment indicated that the model captured the variability of the data better than other models. The results demonstrated the superiority of the proposed model over other mainstream existing models. Through the results of this paper, a more efficient energy data management and consumption plan can be established.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"48 ","pages":"Article 101198"},"PeriodicalIF":5.7,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145109549","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 low-latency and area-efficient QCA-based quantum-dot design for next-generation digital sustainable systems 基于量子点的低延迟和面积高效量子点设计，用于下一代数字可持续系统

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

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-09 DOI: 10.1016/j.suscom.2025.101204

Muhammad Zohaib , Seyed-Sajad Ahmadpour , Hadi Rasmi , Angshuman Khan , Nima Jafari Navimipour

Digital sustainable system plays a vital role in the advancement of dynamic industries, including agriculture, healthcare, smart cities, Edge Artificial Intelligence (AI), and the Internet of Things (IoT), by facilitating high-speed, low-power, and highly compressed processing. These systems are based on the capabilities of real-time execution, processing, and analysis of large-scale information with extreme power and area limitations. However, traditional Arithmetic Logic Units (ALUs) based on complementary metal-oxide semiconductors (CMOS) are becoming challenging in terms of scalability, power consumption, space demand, and nanoscale fabrication. The ALU is one of the most important parts of such systems and has a direct effect on the overall computing performance, but current implementations cannot sustain the requirements of next-generation applications. To overcome these shortcomings, this paper offers an area-efficient and low-latency ALU that can be designed with the quantum-dot cellular automata (QCA) technology, with the advantage of employing area-efficient layout and simple cell design. The proposed QCA-based ALU has high performance, less delay, and less energy consumption, which makes it properly suitable for the next generation of digital sustainable systems applications. The outcome of the simulation indicates that there are considerable performance gains, such as an 82.37% decrease in energy consumption, and a 9.21% decrease in area relative to current available design. These enhancements emphasize the power of QCA technology as a scalable and low-energy consumption alternative to CMOS in the realization of critical computing components in sustainable digital systems.

数字可持续系统通过促进高速、低功耗和高度压缩的处理，在农业、医疗保健、智慧城市、边缘人工智能（AI）和物联网（IoT）等动态行业的发展中发挥着至关重要的作用。这些系统基于实时执行、处理和分析具有极限功率和面积限制的大规模信息的能力。然而，传统的基于互补金属氧化物半导体（CMOS）的算术逻辑单元（alu）在可扩展性、功耗、空间需求和纳米级制造方面正变得具有挑战性。ALU是此类系统中最重要的部分之一，对整体计算性能有直接影响，但目前的实现无法满足下一代应用程序的需求。为了克服这些缺点，本文提出了一种利用量子点元胞自动机（QCA）技术设计的面积高效、低延迟的ALU，该ALU具有面积高效布局和单元设计简单的优点。所提出的基于qca的ALU具有高性能、低时延、低能耗等特点，适合于下一代数字可持续系统的应用。仿真结果表明，相对于当前可用的设计，该方案具有相当大的性能提升，如能耗降低82.37%，面积减少9.21%。这些增强强调了QCA技术在实现可持续数字系统中的关键计算组件方面作为CMOS的可扩展和低能耗替代品的能力。

{"title":"A low-latency and area-efficient QCA-based quantum-dot design for next-generation digital sustainable systems","authors":"Muhammad Zohaib , Seyed-Sajad Ahmadpour , Hadi Rasmi , Angshuman Khan , Nima Jafari Navimipour","doi":"10.1016/j.suscom.2025.101204","DOIUrl":"10.1016/j.suscom.2025.101204","url":null,"abstract":"<div><div>Digital sustainable system plays a vital role in the advancement of dynamic industries, including agriculture, healthcare, smart cities, Edge Artificial Intelligence (AI), and the Internet of Things (IoT), by facilitating high-speed, low-power, and highly compressed processing. These systems are based on the capabilities of real-time execution, processing, and analysis of large-scale information with extreme power and area limitations. However, traditional Arithmetic Logic Units (ALUs) based on complementary metal-oxide semiconductors (CMOS) are becoming challenging in terms of scalability, power consumption, space demand, and nanoscale fabrication. The ALU is one of the most important parts of such systems and has a direct effect on the overall computing performance, but current implementations cannot sustain the requirements of next-generation applications. To overcome these shortcomings, this paper offers an area-efficient and low-latency ALU that can be designed with the quantum-dot cellular automata (QCA) technology, with the advantage of employing area-efficient layout and simple cell design. The proposed QCA-based ALU has high performance, less delay, and less energy consumption, which makes it properly suitable for the next generation of digital sustainable systems applications. The outcome of the simulation indicates that there are considerable performance gains, such as an 82.37% decrease in energy consumption, and a 9.21% decrease in area relative to current available design. These enhancements emphasize the power of QCA technology as a scalable and low-energy consumption alternative to CMOS in the realization of critical computing components in sustainable digital systems.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"48 ","pages":"Article 101204"},"PeriodicalIF":5.7,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096419","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

Optimizing regional energy systems with concentrated solar power for enhanced efficiency, sustainability, and cost-effective energy management 利用聚光太阳能优化区域能源系统，提高效率、可持续性和成本效益

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

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-09 DOI: 10.1016/j.suscom.2025.101205

Songzhi Zhang, Peng Sun

The current study optimizes a regional integrated energy system that combines concentrated solar power, wind turbines, energy storage, and thermal components to enhance energy efficiency, reduce costs, and minimize environmental impact. The primary objectives were to reduce operational expenses, address environmental concerns, and ensure a reliable electricity supply through integrated load response mechanisms. Fuzzy probability-constrained programming was used to model the uncertainty of renewable energy output, and a modified gravitational search algorithm (MGSA) was employed for optimization. Two different approaches to energy demand response were studied: one using electric boilers with a fixed thermoelectric power ratio, and another employing a flexible system for cooling, heating, and power that could adjust as needed. The implementation of the load response program resulted in a 0.75 % increase in the electrical peak-valley difference and a 0.51 % increase in the thermal peak-valley difference, indicating slight shifts in demand distribution. Additionally, valley values decreased by 0.37 % for electrical loads and by 2.71 % for thermal loads, suggesting modest improvements in off-peak load utilization. These changes demonstrate the program's potential to reshape load profiles; however, significant peak reduction will require further enhancement.

目前的研究优化了一个区域综合能源系统，该系统结合了聚光太阳能、风力涡轮机、能源储存和热组件，以提高能源效率、降低成本并最大限度地减少对环境的影响。主要目标是减少运营费用，解决环境问题，并通过综合负荷响应机制确保可靠的电力供应。采用模糊概率约束规划对可再生能源输出的不确定性进行建模，并采用改进的引力搜索算法（MGSA）进行优化。研究了两种不同的能源需求响应方法：一种是使用固定热电功率比的电锅炉，另一种是采用可根据需要调整的灵活系统进行冷却、加热和供电。负荷响应方案的实施导致电峰谷差增加了0.75 %，热峰谷差增加了0.51 %，这表明需求分布略有变化。此外，电力负荷的谷值下降了0.37 %，热负荷的谷值下降了2.71 %，表明非峰负荷利用率略有提高。这些变化表明，该计划的潜力，重塑负荷概况；然而，显著的峰值降低需要进一步的增强。

{"title":"Optimizing regional energy systems with concentrated solar power for enhanced efficiency, sustainability, and cost-effective energy management","authors":"Songzhi Zhang, Peng Sun","doi":"10.1016/j.suscom.2025.101205","DOIUrl":"10.1016/j.suscom.2025.101205","url":null,"abstract":"<div><div>The current study optimizes a regional integrated energy system that combines concentrated solar power, wind turbines, energy storage, and thermal components to enhance energy efficiency, reduce costs, and minimize environmental impact. The primary objectives were to reduce operational expenses, address environmental concerns, and ensure a reliable electricity supply through integrated load response mechanisms. Fuzzy probability-constrained programming was used to model the uncertainty of renewable energy output, and a modified gravitational search algorithm (MGSA) was employed for optimization. Two different approaches to energy demand response were studied: one using electric boilers with a fixed thermoelectric power ratio, and another employing a flexible system for cooling, heating, and power that could adjust as needed. The implementation of the load response program resulted in a 0.75 % increase in the electrical peak-valley difference and a 0.51 % increase in the thermal peak-valley difference, indicating slight shifts in demand distribution. Additionally, valley values decreased by 0.37 % for electrical loads and by 2.71 % for thermal loads, suggesting modest improvements in off-peak load utilization. These changes demonstrate the program's potential to reshape load profiles; however, significant peak reduction will require further enhancement.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"48 ","pages":"Article 101205"},"PeriodicalIF":5.7,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145118049","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

Nonlinear energy modeling for UAVs in critical missions using multiplicative calculus 基于乘法演算的无人机关键任务非线性能量建模

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

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-08 DOI: 10.1016/j.suscom.2025.101206

Özlem Sabuncu , Bülent Bilgehan

Energy efficiency in Unmanned Aerial Vehicles (UAVs) is crucial for operations, where effective payload delivery, stabilization, and communication are essential. This study presents a nonlinear energy consumption model tailored for UAVs, built upon exponential scaling and multiplicative calculus to reflect the interdependencies among payload weight, wind speed, altitude, velocity and communication power. Unlike conventional approaches that rely on linear or polynomial formulations, the proposed method incorporates energy demands from integrated systems, focusing on energy consumption. The proposed multiplicative model provides valuable insights into the energy trade-offs influenced by changing environmental and operational conditions. It improves the practicality of using UAVs for real-time aid delivery, resource allocation, and communication in challenging, resource-constrained environments, offering better accuracy than traditional energy consumption models. Validation using experimental datasets demonstrates that the proposed model achieves an 85 % improvement in accuracy compared to the recently established cubic polynomial model for predicting energy consumption. The effectiveness of the proposed multiplicative model was evaluated using Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) as performance metrics. The basic polynomial model recorded an MSE of 57.4269, while the parametric polynomial model significantly improved this to 5.7794. In comparison, the multiplicative model demonstrated superior accuracy, achieving a markedly lower MSE of 0.8472. Consistently, the multiplicative model also outperformed the others in terms of RMSE, attaining the lowest value of 0.9205, thereby confirming its robustness and predictive reliability. The Mean Absolute Error (MAE) was reduced from 6.44 to 0.73, representing an 88.66 % improvement. Furthermore, the R² value increased from 0.95 to 0.99, indicating a stronger fit between the predicted and actual data. These results underscore the multiplicative model's robustness, accuracy, and reliability, demonstrating its strong potential for real-world predictive applications. The findings demonstrate that the proposed model more accurately represents energy consumption, providing a robust foundation for precise analysis and design.

无人机（uav）的能源效率对作战至关重要，其中有效的有效载荷交付、稳定和通信至关重要。为反映无人机载荷重量、风速、高度、速度和通信功率之间的相互依赖关系，提出了一种基于指数标度和乘法演算的无人机非线性能耗模型。与依赖线性或多项式公式的传统方法不同，该方法结合了集成系统的能源需求，重点关注能源消耗。所提出的乘法模型对受变化的环境和操作条件影响的能源权衡提供了有价值的见解。它提高了在具有挑战性、资源受限的环境中使用无人机进行实时援助交付、资源分配和通信的实用性，比传统的能源消耗模型提供了更好的准确性。使用实验数据集的验证表明，与最近建立的用于预测能耗的三次多项式模型相比，所提出的模型的精度提高了85 %。使用均方误差（MSE）和均方根误差（RMSE）作为性能指标来评估所提出的乘法模型的有效性。基本多项式模型的MSE为57.4269，而参数多项式模型将其显著提高到5.7794。相比之下，乘法模型表现出更高的准确性，实现了0.8472的显著较低的MSE。同样，乘法模型在RMSE方面也优于其他模型，其RMSE最小值为0.9205，从而证实了其稳健性和预测可靠性。平均绝对误差（MAE）从6.44降低到0.73，改善了88.66 %。R²值从0.95增加到0.99，表明预测数据与实际数据的拟合程度较好。这些结果强调了乘法模型的稳健性、准确性和可靠性，展示了其在现实世界预测应用中的强大潜力。研究结果表明，该模型更准确地反映了能源消耗，为精确分析和设计提供了坚实的基础。

{"title":"Nonlinear energy modeling for UAVs in critical missions using multiplicative calculus","authors":"Özlem Sabuncu , Bülent Bilgehan","doi":"10.1016/j.suscom.2025.101206","DOIUrl":"10.1016/j.suscom.2025.101206","url":null,"abstract":"<div><div>Energy efficiency in Unmanned Aerial Vehicles (UAVs) is crucial for operations, where effective payload delivery, stabilization, and communication are essential. This study presents a nonlinear energy consumption model tailored for UAVs, built upon exponential scaling and multiplicative calculus to reflect the interdependencies among payload weight, wind speed, altitude, velocity and communication power. Unlike conventional approaches that rely on linear or polynomial formulations, the proposed method incorporates energy demands from integrated systems, focusing on energy consumption. The proposed multiplicative model provides valuable insights into the energy trade-offs influenced by changing environmental and operational conditions. It improves the practicality of using UAVs for real-time aid delivery, resource allocation, and communication in challenging, resource-constrained environments, offering better accuracy than traditional energy consumption models. Validation using experimental datasets demonstrates that the proposed model achieves an 85 % improvement in accuracy compared to the recently established cubic polynomial model for predicting energy consumption. The effectiveness of the proposed multiplicative model was evaluated using Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) as performance metrics. The basic polynomial model recorded an MSE of 57.4269, while the parametric polynomial model significantly improved this to 5.7794. In comparison, the multiplicative model demonstrated superior accuracy, achieving a markedly lower MSE of 0.8472. Consistently, the multiplicative model also outperformed the others in terms of RMSE, attaining the lowest value of 0.9205, thereby confirming its robustness and predictive reliability. The Mean Absolute Error (MAE) was reduced from 6.44 to 0.73, representing an 88.66 % improvement. Furthermore, the R² value increased from 0.95 to 0.99, indicating a stronger fit between the predicted and actual data. These results underscore the multiplicative model's robustness, accuracy, and reliability, demonstrating its strong potential for real-world predictive applications. The findings demonstrate that the proposed model more accurately represents energy consumption, providing a robust foundation for precise analysis and design.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"48 ","pages":"Article 101206"},"PeriodicalIF":5.7,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145060496","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