Sustainable Computing-Informatics & Systems最新文献_第10页

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 : 2025-12-01 Epub 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":"2025-12-01","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

Stability improvement of multimachine power system using DRL based wind-PV-controller 基于DRL的风电-光伏控制器对多机电力系统稳定性的改善

IF 3.8 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-01 Epub Date: 2025-07-15 DOI: 10.1016/j.suscom.2025.101168

Deshveer Narwal, Deepesh Sharma

A significant challenge in modern electric power grids is the stability of power systems, particularly under extreme events such as demand surges and disruptions. Integrating renewable energy into the current system present a viable approach for meeting the growing demand. Furthermore, apart from efficiently meeting the increasing need, these renewable energy systems, with their supplementary circuitry, can substantially improve the stability of the power system. This research suggests a new method that combines deep reinforcement learning (DRL) with a Fractional Order deep Q network (FO-DQN) to address stability problems in multimachine power systems. Incorporating wind and PV systems, which function as STATCOM when necessary, introduces intricacy to the system's dynamics. The proposed DRL based controller facilitates dynamic real-time control of power flow, guaranteeing voltage stability throughout the system. The controller based on DRL is able to autonomously modify the settings of the PV Static Synchronous Compensator (STATCOM) and unified inter-phase power controller (UIPC) operated wind turbine (WT) system. This adjustment helps to provide reactive power compensation and stabilize the system during extreme conditions. This results in a high level of resilience and flexibility. The efficacy of the suggested approach for enhancing stability of multimachine power systems is proven through thorough simulations and comparative analysis. The results demonstrate higher system performance, reduced voltage drop, and optimal reactive power compensation in the presence of diverse operating circumstances and disturbances (fault).

现代电网面临的一个重大挑战是电力系统的稳定性，特别是在需求激增和中断等极端事件下。将可再生能源纳入现有系统是满足日益增长的需求的可行方法。此外，除了有效地满足日益增长的需求外，这些可再生能源系统及其补充电路可以大大提高电力系统的稳定性。本文提出了一种将深度强化学习（DRL）与分数阶深度Q网络（FO-DQN）相结合的新方法来解决多机电力系统的稳定性问题。结合风能和光伏系统，必要时作为STATCOM的功能，引入了系统动态的复杂性。本文提出的基于DRL的控制器可以实现潮流的动态实时控制，保证整个系统的电压稳定。基于DRL的控制器能够自主修改光伏静态同步补偿器（STATCOM）和统一相间功率控制器（UIPC）运行的风力发电机组（WT）系统的设置。这种调整有助于在极端条件下提供无功补偿和稳定系统。这导致了高水平的弹性和灵活性。通过仿真和对比分析，证明了该方法对提高多机电力系统稳定性的有效性。结果表明，在各种运行环境和干扰（故障）存在的情况下，系统性能更高，电压降降低，无功补偿最佳。

{"title":"Stability improvement of multimachine power system using DRL based wind-PV-controller","authors":"Deshveer Narwal, Deepesh Sharma","doi":"10.1016/j.suscom.2025.101168","DOIUrl":"10.1016/j.suscom.2025.101168","url":null,"abstract":"<div><div>A significant challenge in modern electric power grids is the stability of power systems, particularly under extreme events such as demand surges and disruptions. Integrating renewable energy into the current system present a viable approach for meeting the growing demand. Furthermore, apart from efficiently meeting the increasing need, these renewable energy systems, with their supplementary circuitry, can substantially improve the stability of the power system. This research suggests a new method that combines deep reinforcement learning (DRL) with a Fractional Order deep Q network (FO-DQN) to address stability problems in multimachine power systems. Incorporating wind and PV systems, which function as STATCOM when necessary, introduces intricacy to the system's dynamics. The proposed DRL based controller facilitates dynamic real-time control of power flow, guaranteeing voltage stability throughout the system. The controller based on DRL is able to autonomously modify the settings of the PV Static Synchronous Compensator (STATCOM) and unified inter-phase power controller (UIPC) operated wind turbine (WT) system. This adjustment helps to provide reactive power compensation and stabilize the system during extreme conditions. This results in a high level of resilience and flexibility. The efficacy of the suggested approach for enhancing stability of multimachine power systems is proven through thorough simulations and comparative analysis. The results demonstrate higher system performance, reduced voltage drop, and optimal reactive power compensation in the presence of diverse operating circumstances and disturbances (fault).</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101168"},"PeriodicalIF":3.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144694907","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

DT-GWO: A hybrid decision tree and GWO-based algorithm for multi-objective task scheduling optimization in cloud computing DT-GWO：一种基于混合决策树和gwo的云计算多目标任务调度优化算法

IF 3.8 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-01 Epub Date: 2025-05-20 DOI: 10.1016/j.suscom.2025.101138

Mohaymen Selselejoo, HamidReza Ahmadifar

Cloud computing faces significant challenges in task management, particularly in balancing server loads to prevent both overload and underload conditions while meeting diverse quality of service requirements. The need to manage multiple criteria further increases the complexity of this problem. Additionally, the heterogeneity of cloud resources often complicates efficient task scheduling. To overcome these challenges, this paper introduces a hybrid model that integrates the decision tree approach with the Grey Wolf Optimization (GWO) algorithm for the scheduling of independent tasks. The model aims to optimize makespan, reduce total cost, enhance resource utilization, and maintain load balance. In the proposed approach, tasks are first classified using a decision tree, after which the GWO algorithm allocates resources to the selected tasks. Simulations are conducted using the CloudSim toolkit, in a heterogeneous environment. The experiments consider various input scenarios, ranging from 200 to 3200 tasks. Compared to the standalone GWO algorithm, the proposed DT-GWO hybrid model achieves improvements of at least 18.5 % in makespan, 3.4 % in average resource utilization, and 12.7 % in total cost, all while maintaining load balance.

云计算在任务管理方面面临重大挑战，特别是在平衡服务器负载以防止过载和负载不足的情况下，同时满足不同的服务质量要求。管理多个标准的需要进一步增加了这个问题的复杂性。此外，云资源的异构性通常会使有效的任务调度变得复杂。为了克服这些挑战，本文引入了一种将决策树方法与灰狼优化（GWO）算法相结合的混合模型，用于独立任务的调度。该模型以优化makespan、降低总成本、提高资源利用率和保持负载平衡为目标。在该方法中，首先使用决策树对任务进行分类，然后GWO算法将资源分配给选定的任务。在异构环境中使用CloudSim工具包进行模拟。实验考虑了不同的输入场景，从200到3200个任务不等。与单独的GWO算法相比，本文提出的DT-GWO混合模型在保持负载平衡的情况下，完成时间至少提高18.5 %，平均资源利用率提高3.4 %，总成本提高12.7 %。

{"title":"DT-GWO: A hybrid decision tree and GWO-based algorithm for multi-objective task scheduling optimization in cloud computing","authors":"Mohaymen Selselejoo, HamidReza Ahmadifar","doi":"10.1016/j.suscom.2025.101138","DOIUrl":"10.1016/j.suscom.2025.101138","url":null,"abstract":"<div><div>Cloud computing faces significant challenges in task management, particularly in balancing server loads to prevent both overload and underload conditions while meeting diverse quality of service requirements. The need to manage multiple criteria further increases the complexity of this problem. Additionally, the heterogeneity of cloud resources often complicates efficient task scheduling. To overcome these challenges, this paper introduces a hybrid model that integrates the decision tree approach with the Grey Wolf Optimization (GWO) algorithm for the scheduling of independent tasks. The model aims to optimize makespan, reduce total cost, enhance resource utilization, and maintain load balance. In the proposed approach, tasks are first classified using a decision tree, after which the GWO algorithm allocates resources to the selected tasks. Simulations are conducted using the CloudSim toolkit, in a heterogeneous environment. The experiments consider various input scenarios, ranging from 200 to 3200 tasks. Compared to the standalone GWO algorithm, the proposed DT-GWO hybrid model achieves improvements of at least 18.5 % in makespan, 3.4 % in average resource utilization, and 12.7 % in total cost, all while maintaining load balance.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101138"},"PeriodicalIF":3.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144106842","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

Multi-heterogeneous renewable energy scheduling optimization based on time series algorithm and green computing-driven sustainable development 基于时间序列算法的多异构可再生能源调度优化与绿色计算驱动的可持续发展

IF 3.8 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-01 Epub Date: 2025-07-17 DOI: 10.1016/j.suscom.2025.101173

Chaoran Ma , Puguang Hou

The integration of heterogeneous renewable energy sources, such as wind and solar, poses significant challenges to the dynamic economic and environmental dispatch of power systems due to their intermittent and uncertain nature. Efficient coordination between generation and consumption is crucial to ensure stability, reduce emissions, and lower costs. Accurate forecasting of renewable outputs is a critical prerequisite for achieving optimal dispatch decisions. To address this, we propose a hybrid prediction and scheduling framework that leverages time series forecasting to support real-time dispatch optimization. Specifically, we develop a novel prediction model based on a Completely Input and Output-connected Long Short-Term Memory (CIAO-LSTM) network, whose parameters are optimized using an Improved Fruit Fly Optimization Algorithm (IFOA). This approach enhances the model’s ability to capture both linear and nonlinear temporal features and improves convergence through adaptive search strategies. The predicted outputs are then incorporated into a rolling real-time scheduling model that jointly minimizes generation costs and pollutant emissions. Simulation results on a six-unit power system demonstrate that our approach significantly improves prediction accuracy and dispatch performance, reducing average generation costs and emissions by over 8 % and 16 %, respectively. These results confirm the effectiveness of the proposed method in promoting green and sustainable power systems.

风能和太阳能等异质可再生能源的整合，由于其间歇性和不确定性，对电力系统的动态经济和环境调度提出了重大挑战。发电和用电之间的有效协调对于确保稳定、减少排放和降低成本至关重要。可再生能源产出的准确预测是实现最优调度决策的关键先决条件。为了解决这个问题，我们提出了一个混合预测和调度框架，利用时间序列预测来支持实时调度优化。具体而言，我们建立了一种基于完全输入输出连接的长短期记忆（CIAO-LSTM）网络的预测模型，该模型的参数使用改进的果蝇优化算法（IFOA）进行优化。该方法增强了模型捕捉线性和非线性时间特征的能力，并通过自适应搜索策略提高了收敛性。然后将预测输出纳入滚动实时调度模型，以共同最小化发电成本和污染物排放。在一个六机组电力系统上的仿真结果表明，该方法显著提高了预测精度和调度性能，平均发电成本和排放分别降低了8% %和16% %。这些结果证实了所提出的方法在促进绿色和可持续电力系统方面的有效性。

{"title":"Multi-heterogeneous renewable energy scheduling optimization based on time series algorithm and green computing-driven sustainable development","authors":"Chaoran Ma , Puguang Hou","doi":"10.1016/j.suscom.2025.101173","DOIUrl":"10.1016/j.suscom.2025.101173","url":null,"abstract":"<div><div>The integration of heterogeneous renewable energy sources, such as wind and solar, poses significant challenges to the dynamic economic and environmental dispatch of power systems due to their intermittent and uncertain nature. Efficient coordination between generation and consumption is crucial to ensure stability, reduce emissions, and lower costs. Accurate forecasting of renewable outputs is a critical prerequisite for achieving optimal dispatch decisions. To address this, we propose a hybrid prediction and scheduling framework that leverages time series forecasting to support real-time dispatch optimization. Specifically, we develop a novel prediction model based on a Completely Input and Output-connected Long Short-Term Memory (CIAO-LSTM) network, whose parameters are optimized using an Improved Fruit Fly Optimization Algorithm (IFOA). This approach enhances the model’s ability to capture both linear and nonlinear temporal features and improves convergence through adaptive search strategies. The predicted outputs are then incorporated into a rolling real-time scheduling model that jointly minimizes generation costs and pollutant emissions. Simulation results on a six-unit power system demonstrate that our approach significantly improves prediction accuracy and dispatch performance, reducing average generation costs and emissions by over 8 % and 16 %, respectively. These results confirm the effectiveness of the proposed method in promoting green and sustainable power systems.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101173"},"PeriodicalIF":3.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144695325","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

Blockchain-integrated decentralized fault tolerance for secure and energy-efficient multi-cloud interoperability 区块链集成去中心化容错，实现安全高效的多云互操作性

IF 3.8 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-01 Epub Date: 2025-07-16 DOI: 10.1016/j.suscom.2025.101170

V.M. Sivagami , K.S. EaswaraKumar , D. Jayanthi , S. Kalavathi

Cloud service provider, multi-cloud scheme has become a strategic fashion to maximize reliability, affordability, and performance. To pose major difficulties with regard to fault tolerance, interoperability, security, and muscularity economy. To address these issues, this employment suggests a unique blockchain-integrated decentralized error allowance system. The advice model uses Proof of Stake (PoS) as the consensus chemical mechanism to improve DOE economy while preserving strong security measure and performance criteria. By around 30 %, smart contracts help to automatically reclaim defect, therefore greatly let down migration costs and downtime. To guarantee data integrity and secrecy across heterogenous swarm environs, the model as well flux a multi-layered security computer architecture desegregate homomorphic encryption, Zero-Knowledge Proofs (ZKP), and Decentralized Identity (DIDs). Atomic swop and cross-chain bridgework avail to enable cross-chain interoperability, hence enabling flawless and good data point exchanges with lower limit delay. Validating the achiever of the indicate strategy, the data-based finding point important addition in free energy efficiency, certificate success rate outdo 90 %, and lour migration costs. These results show the hypothesis of the suggested model to change multi-cloud direction strategies, thereby offering a strong ground for future investigations and practical applications.

云服务提供商，多云方案已成为最大限度地提高可靠性、可负担性和性能的战略时尚。在容错、互操作性、安全性和肌肉经济性方面提出主要困难。为了解决这些问题，这项工作提出了一种独特的区块链集成分散错误允许系统。该建议模型使用权益证明（PoS）作为共识化学机制，以提高DOE经济性，同时保持强大的安全措施和性能标准。大约30% %，智能合约有助于自动回收缺陷，因此大大降低了迁移成本和停机时间。为了保证异构群体环境中的数据完整性和保密性，该模型还采用了多层安全计算机体系结构，消除了同态加密、零知识证明（ZKP）和分散身份（did）。原子交换和跨链桥接有助于实现跨链互操作性，从而实现具有下限延迟的完美和良好的数据点交换。验证了指示策略的完成者，基于数据的寻点在自由能源效率、证书成功率超过90% %、人力迁移成本等方面有重要的增加。这些结果证明了所建议模型的假设能够改变多云方向策略，从而为未来的研究和实际应用提供了坚实的基础。

{"title":"Blockchain-integrated decentralized fault tolerance for secure and energy-efficient multi-cloud interoperability","authors":"V.M. Sivagami , K.S. EaswaraKumar , D. Jayanthi , S. Kalavathi","doi":"10.1016/j.suscom.2025.101170","DOIUrl":"10.1016/j.suscom.2025.101170","url":null,"abstract":"<div><div>Cloud service provider, multi-cloud scheme has become a strategic fashion to maximize reliability, affordability, and performance. To pose major difficulties with regard to fault tolerance, interoperability, security, and muscularity economy. To address these issues, this employment suggests a unique blockchain-integrated decentralized error allowance system. The advice model uses Proof of Stake (PoS) as the consensus chemical mechanism to improve DOE economy while preserving strong security measure and performance criteria. By around 30 %, smart contracts help to automatically reclaim defect, therefore greatly let down migration costs and downtime. To guarantee data integrity and secrecy across heterogenous swarm environs, the model as well flux a multi-layered security computer architecture desegregate homomorphic encryption, Zero-Knowledge Proofs (ZKP), and Decentralized Identity (DIDs). Atomic swop and cross-chain bridgework avail to enable cross-chain interoperability, hence enabling flawless and good data point exchanges with lower limit delay. Validating the achiever of the indicate strategy, the data-based finding point important addition in free energy efficiency, certificate success rate outdo 90 %, and lour migration costs. These results show the hypothesis of the suggested model to change multi-cloud direction strategies, thereby offering a strong ground for future investigations and practical applications.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101170"},"PeriodicalIF":3.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703774","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 microgrid energy management with hybrid energy storage systems using reinforcement learning methods 利用强化学习方法优化混合储能系统微电网能量管理

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

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-01 Epub Date: 2025-07-24 DOI: 10.1016/j.suscom.2025.101177

Lejia Li

With the growth of global energy demand and the pursuit of sustainable energy, microgrids, as an emerging energy supply system, are becoming increasingly important. However, the energy management of microgrid hybrid energy storage systems face numerous challenges, including significant energy waste and poor power supply stability. This study aims to optimize the energy management of microgrid hybrid energy storage systems using reinforcement learning methods. By constructing a reinforcement learning model architecture based on the Markov decision process, the state space, action space, and reward function are systematically designed. The improved proximal policy optimization (PPO) algorithm is then used for implementation. Historical microgrid operation data spanning one year was preprocessed to normalize critical variables, and a simulation was run in a Python environment using OpenAI Gym and proprietary energy system dynamics. The experiment utilizes the operational data of a regional microgrid for one year to compare the traditional model, based on fixed-priority energy allocation rules, with the neural network model. The results show that the reinforcement learning model has an average annual energy management efficiency of 84.5 %, which is significantly improved compared with the 54.25 % of the traditional model and 70 % of the neural network model; the energy loss rate is only 8 %, which is much lower than the 25 % of the traditional model and 18 % of the neural network model; the comprehensive index of power supply stability is 0.92, which is also better than other models. This study provides an efficient and adaptable solution for microgrid energy management, which is expected to promote the healthy development of the microgrid industry.

随着全球能源需求的增长和对可持续能源的追求，微电网作为一种新兴的能源供应系统显得越来越重要。然而，微网混合储能系统的能量管理面临着能源浪费严重、供电稳定性差等诸多挑战。本研究旨在利用强化学习方法优化微电网混合储能系统的能量管理。通过构建基于马尔可夫决策过程的强化学习模型体系结构，系统地设计了状态空间、动作空间和奖励函数。然后使用改进的近端策略优化（PPO）算法进行实现。对微电网一年的历史运行数据进行预处理，对关键变量进行归一化，并使用OpenAI Gym和专有能源系统动力学在Python环境下进行仿真。实验利用某区域微电网一年的运行数据，将基于固定优先级能量分配规则的传统模型与神经网络模型进行对比。结果表明：强化学习模型的年平均能量管理效率为84.5 %，较传统模型的54.25 %和神经网络模型的70 %有显著提高；能量损失率仅为8 %，远低于传统模型的25 %和神经网络模型的18 %；供电稳定性综合指数为0.92，也优于其他模型。本研究为微网能源管理提供了一种高效、适应性强的解决方案，有望促进微网产业的健康发展。

{"title":"Optimizing microgrid energy management with hybrid energy storage systems using reinforcement learning methods","authors":"Lejia Li","doi":"10.1016/j.suscom.2025.101177","DOIUrl":"10.1016/j.suscom.2025.101177","url":null,"abstract":"<div><div>With the growth of global energy demand and the pursuit of sustainable energy, microgrids, as an emerging energy supply system, are becoming increasingly important. However, the energy management of microgrid hybrid energy storage systems face numerous challenges, including significant energy waste and poor power supply stability. This study aims to optimize the energy management of microgrid hybrid energy storage systems using reinforcement learning methods. By constructing a reinforcement learning model architecture based on the Markov decision process, the state space, action space, and reward function are systematically designed. The improved proximal policy optimization (PPO) algorithm is then used for implementation. Historical microgrid operation data spanning one year was preprocessed to normalize critical variables, and a simulation was run in a Python environment using OpenAI Gym and proprietary energy system dynamics. The experiment utilizes the operational data of a regional microgrid for one year to compare the traditional model, based on fixed-priority energy allocation rules, with the neural network model. The results show that the reinforcement learning model has an average annual energy management efficiency of 84.5 %, which is significantly improved compared with the 54.25 % of the traditional model and 70 % of the neural network model; the energy loss rate is only 8 %, which is much lower than the 25 % of the traditional model and 18 % of the neural network model; the comprehensive index of power supply stability is 0.92, which is also better than other models. This study provides an efficient and adaptable solution for microgrid energy management, which is expected to promote the healthy development of the microgrid industry.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101177"},"PeriodicalIF":5.7,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144773133","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

The early warning method for offshore wind turbine gearbox oil temperature based on FSTAE-ATT 基于FSTAE-ATT的海上风电齿轮箱油温预警方法

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

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-01 Epub Date: 2025-08-09 DOI: 10.1016/j.suscom.2025.101180

Anping Wan , Shuai Peng , Khalil AL-Bukhaiti , Yunsong Ji , Shidong Ma

Offshore wind turbine gearboxes often experience malfunctions due to harsh environmental conditions, resulting in significant downtime and financial losses. This study presents an innovative early warning system for monitoring gearbox oil temperature using a novel FSTAE-ATT model. The system leverages SCADA data and employs Feature Mode Decomposition (FMD) to enhance feature extraction from gearbox oil temperature measurements. The FSTAE-ATT model integrates Convolutional Neural Networks (CNN) for spatial feature extraction and Long Short-Term Memory (LSTM) networks for temporal dependencies, augmented by a self-attention mechanism to highlight critical features. The model's reconstruction error serves as an early warning indicator for gearbox oil temperature anomalies. The effectiveness of the FSTAE-ATT model was validated using real-world data from an offshore wind farm in Yangjiang, Guangdong, China. Comparative analysis with other models, including STAE, STAE-ATT, AE, TAE, and SAE, demonstrated that the FSTAE-ATT model outperforms them with lower RMSE (e.g., 0.003452 for unit #40) and MAE (e.g., 0.002828 for unit #40) metrics. Additionally, significantly earlier warning times (e.g., up to 22 h and 36 min for unit #40), provide substantial lead time for preventative maintenance. This work contributes to advancing offshore wind turbine condition monitoring and fault detection, enhancing the sustainability and profitability of offshore wind energy systems.

由于恶劣的环境条件，海上风力涡轮机齿轮箱经常出现故障，导致大量停机和经济损失。本研究提出了一种新颖的FSTAE-ATT模型用于监测变速箱油温的预警系统。该系统利用SCADA数据，并采用特征模式分解（FMD）来增强变速箱油温测量的特征提取。FSTAE-ATT模型集成了用于空间特征提取的卷积神经网络（CNN）和用于时间依赖性提取的长短期记忆（LSTM）网络，并通过自注意机制增强以突出关键特征。该模型的重构误差可作为齿轮箱油温异常的预警指标。利用中国广东阳江海上风电场的实际数据验证了FSTAE-ATT模型的有效性。与其他模型（包括STAE、STAE- att、AE、TAE和SAE）的比较分析表明，FSTAE-ATT模型具有较低的RMSE（例如，单元#40的0.003452）和MAE（例如，单元#40的0.002828）指标，优于它们。此外，更早的预警时间（例如，40号机组高达22 h和36 min），为预防性维护提供了大量的提前时间。这项工作有助于推进海上风电机组状态监测和故障检测，提高海上风电系统的可持续性和盈利能力。

{"title":"The early warning method for offshore wind turbine gearbox oil temperature based on FSTAE-ATT","authors":"Anping Wan , Shuai Peng , Khalil AL-Bukhaiti , Yunsong Ji , Shidong Ma","doi":"10.1016/j.suscom.2025.101180","DOIUrl":"10.1016/j.suscom.2025.101180","url":null,"abstract":"<div><div>Offshore wind turbine gearboxes often experience malfunctions due to harsh environmental conditions, resulting in significant downtime and financial losses. This study presents an innovative early warning system for monitoring gearbox oil temperature using a novel FSTAE-ATT model. The system leverages SCADA data and employs Feature Mode Decomposition (FMD) to enhance feature extraction from gearbox oil temperature measurements. The FSTAE-ATT model integrates Convolutional Neural Networks (CNN) for spatial feature extraction and Long Short-Term Memory (LSTM) networks for temporal dependencies, augmented by a self-attention mechanism to highlight critical features. The model's reconstruction error serves as an early warning indicator for gearbox oil temperature anomalies. The effectiveness of the FSTAE-ATT model was validated using real-world data from an offshore wind farm in Yangjiang, Guangdong, China. Comparative analysis with other models, including STAE, STAE-ATT, AE, TAE, and SAE, demonstrated that the FSTAE-ATT model outperforms them with lower RMSE (e.g., 0.003452 for unit #40) and MAE (e.g., 0.002828 for unit #40) metrics. Additionally, significantly earlier warning times (e.g., up to 22 h and 36 min for unit #40), provide substantial lead time for preventative maintenance. This work contributes to advancing offshore wind turbine condition monitoring and fault detection, enhancing the sustainability and profitability of offshore wind energy systems.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101180"},"PeriodicalIF":5.7,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144826959","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

Fully-connected layers-embedded self-attention optimizer based on quantum-inspired and fuzzy logic for smart household energy management 基于量子启发和模糊逻辑的智能家庭能源管理全连接层嵌入式自关注优化器

IF 3.8 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-01 Epub Date: 2025-05-30 DOI: 10.1016/j.suscom.2025.101151

Lulin Zhao , Linfei Yin

On the road to carbon neutrality, the solution to the power consumption optimization problem of thousands of households is an essential link. This work mainly constructs a mathematical model of a smart household energy management system (HEMS) considering the real-time users’ willingness. The work proposes a fully-connected layers-embedded self-attention optimizer (FCSAO) based on quantum and fuzzy logic for the HEMS models. The FCSAO is an optimization method accelerated by fully-connected layers-embedded self-attention networks (FCSANs), quantum-inspired logic, and fuzzy logic. In a conventional optimization algorithm iteration process, a generative adversarial network incorporating a self-attention mechanism is adopted to characterize the input-output relationship of the optimization problem, and a quantum universal gate is employed to train the deep network by dividing the dataset into four classes based on the output of the optimization problem. The trained deep network can accelerate the iterative process of traditional optimization algorithm. The smart HEMS divides the loads in the home into rigid loads, adjustable loads, and air conditioner loads. The smart HEMS model meets the goals of users to save electrical energy and reduce electricity price expenditure by the proposed FCSAO based on quantum-inspired and fuzzy logic. Besides, the smart HEMS model can effectively control the operation state of the air conditioner and give the optimal operation time of adjustable loads. Furthermore, with three different scenarios simulated in MATLAB, the optimized indoor temperature meets users’ willingness for temperature comfort level by the proposed FCSAO based on quantum-inspired and fuzzy logic with great expression capability; the proposed FCSAO saves 1.05 % electricity cost.

在碳中和的道路上，解决千家万户的用电优化问题是必不可少的一环。本文主要构建了考虑实时用户意愿的智能家庭能源管理系统（HEMS）数学模型。本文提出了一种基于量子和模糊逻辑的全连接层嵌入式自关注优化器（FCSAO）。FCSAO是一种由全连接层嵌入自关注网络（fcsan）、量子启发逻辑和模糊逻辑加速的优化方法。在传统的优化算法迭代过程中，采用结合自关注机制的生成对抗网络来表征优化问题的输入输出关系，并基于优化问题的输出将数据集划分为四类，采用量子通用门来训练深度网络。训练后的深度网络可以加速传统优化算法的迭代过程。智能HEMS将家庭负荷分为刚性负荷、可调负荷和空调负荷。智能HEMS模型通过提出的基于量子启发和模糊逻辑的FCSAO实现了用户节约电能和降低电价支出的目标。此外，智能HEMS模型可以有效地控制空调的运行状态，给出可调负荷的最佳运行时间。在MATLAB中对三种不同的场景进行了仿真，结果表明，基于量子启发和模糊逻辑的FCSAO优化后的室内温度满足用户对温度舒适度的要求，具有较强的表达能力；建议的FCSAO节省1.05 %的电费。

{"title":"Fully-connected layers-embedded self-attention optimizer based on quantum-inspired and fuzzy logic for smart household energy management","authors":"Lulin Zhao , Linfei Yin","doi":"10.1016/j.suscom.2025.101151","DOIUrl":"10.1016/j.suscom.2025.101151","url":null,"abstract":"<div><div>On the road to carbon neutrality, the solution to the power consumption optimization problem of thousands of households is an essential link. This work mainly constructs a mathematical model of a smart household energy management system (HEMS) considering the real-time users’ willingness. The work proposes a fully-connected layers-embedded self-attention optimizer (FCSAO) based on quantum and fuzzy logic for the HEMS models. The FCSAO is an optimization method accelerated by fully-connected layers-embedded self-attention networks (FCSANs), quantum-inspired logic, and fuzzy logic. In a conventional optimization algorithm iteration process, a generative adversarial network incorporating a self-attention mechanism is adopted to characterize the input-output relationship of the optimization problem, and a quantum universal gate is employed to train the deep network by dividing the dataset into four classes based on the output of the optimization problem. The trained deep network can accelerate the iterative process of traditional optimization algorithm. The smart HEMS divides the loads in the home into rigid loads, adjustable loads, and air conditioner loads. The smart HEMS model meets the goals of users to save electrical energy and reduce electricity price expenditure by the proposed FCSAO based on quantum-inspired and fuzzy logic. Besides, the smart HEMS model can effectively control the operation state of the air conditioner and give the optimal operation time of adjustable loads. Furthermore, with three different scenarios simulated in MATLAB, the optimized indoor temperature meets users’ willingness for temperature comfort level by the proposed FCSAO based on quantum-inspired and fuzzy logic with great expression capability; the proposed FCSAO saves 1.05 % electricity cost.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101151"},"PeriodicalIF":3.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205201","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

Multi-objective hybrid green anaconda skill optimization enabled energy and cache based QoS aware routing in delay tolerant–IoT network 多目标混合绿蟒蛇技能优化实现了容延迟物联网网络中基于能量和缓存的QoS感知路由

IF 3.8 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-01 Epub Date: 2025-06-25 DOI: 10.1016/j.suscom.2025.101158

Ashapu Bhavani , Attada Venkataramana , A.S.N. Chakravarthy

Delay-Tolerant Network (DTN) is developed to overcome the challenges of environments where classical networking models fail due to unstable connectivity and high latency. The DTN offers stable connections between nodes and operates effectively in scenarios where nodes frequently experience disruptions or only sporadic communication opportunities. However, the classical techniques allowed limited data communication and did not apply to the network with reduced resources and which had low delivery rates and high delays. Therefore, this research aims to develop a Green Anaconda Skill Optimization (GASO) for an eQoS-aware routing solution for a DTN-IoT network. Initially, the DTN-IoT network is simulated by considering energy and mobility models. Then, for predicting the energy, Recurrent Radial Basis Function Networks (RRBFN) is used. After that, Cluster Head (CH) selection is executed by GASO, considering multiple objectives, like cache ratio, residual energy, predicted energy, throughput, distance, trust factors, and delay. Finally, GASO is employed for routing, and the above-mentioned multi-objectives are considered. Here, the GASO is established through the fusion of Green Anaconda Optimization (GAO) and Skill Optimization Algorithm (SOA). The evaluation results highlight that the GASO accomplished a reduced distance of 0.253 m, low energy consumption of 0.783 J, and minimal delay of 0.270 sec, with an increased throughput of 0.313 Mbps.

容忍延迟网络（Delay-Tolerant Network， DTN）是为了克服传统网络模型因连接不稳定和时延高而无法实现的环境挑战而开发的。DTN在节点之间提供稳定的连接，并在节点频繁中断或只有零星通信机会的情况下有效运行。然而，传统技术允许有限的数据通信，并不适用于资源较少、传输速率低、延迟高的网络。因此，本研究旨在为DTN-IoT网络的eqos感知路由解决方案开发绿色蟒蛇技能优化（GASO）。首先，通过考虑能源和移动模型来模拟DTN-IoT网络。然后，利用循环径向基函数网络（RRBFN）进行能量预测。之后，由GASO执行簇头（CH）选择，考虑多个目标，如缓存比、剩余能量、预测能量、吞吐量、距离、信任因素和延迟。最后，采用GASO进行路由，并考虑了上述多目标。本文将绿色蟒蛇优化算法（Green Anaconda Optimization， GAO）和技能优化算法（Skill Optimization Algorithm， SOA）融合，建立了GASO。评估结果表明，GASO实现了0.253 m的距离缩短，0.783 J的能耗降低，0.270 秒的最小延迟，吞吐量提高了0.313 Mbps。

{"title":"Multi-objective hybrid green anaconda skill optimization enabled energy and cache based QoS aware routing in delay tolerant–IoT network","authors":"Ashapu Bhavani , Attada Venkataramana , A.S.N. Chakravarthy","doi":"10.1016/j.suscom.2025.101158","DOIUrl":"10.1016/j.suscom.2025.101158","url":null,"abstract":"<div><div>Delay-Tolerant Network (DTN) is developed to overcome the challenges of environments where classical networking models fail due to unstable connectivity and high latency. The DTN offers stable connections between nodes and operates effectively in scenarios where nodes frequently experience disruptions or only sporadic communication opportunities. However, the classical techniques allowed limited data communication and did not apply to the network with reduced resources and which had low delivery rates and high delays. Therefore, this research aims to develop a Green Anaconda Skill Optimization (GASO) for an eQoS-aware routing solution for a DTN-IoT network. Initially, the DTN-IoT network is simulated by considering energy and mobility models. Then, for predicting the energy, Recurrent Radial Basis Function Networks (RRBFN) is used. After that, Cluster Head (CH) selection is executed by GASO, considering multiple objectives, like cache ratio, residual energy, predicted energy, throughput, distance, trust factors, and delay. Finally, GASO is employed for routing, and the above-mentioned multi-objectives are considered. Here, the GASO is established through the fusion of Green Anaconda Optimization (GAO) and Skill Optimization Algorithm (SOA). The evaluation results highlight that the GASO accomplished a reduced distance of 0.253 m, low energy consumption of 0.783 J, and minimal delay of 0.270 sec, with an increased throughput of 0.313 Mbps.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101158"},"PeriodicalIF":3.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144534814","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

Decentralized energy-efficient microgrid control Using Graph neural networks and LSTM-based Event-Triggered control 基于图神经网络和lstm的分散节能微电网控制

IF 3.8 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Sustainable Computing-Informatics & Systems

Pub Date : 2025-09-01 Epub Date: 2025-06-13 DOI: 10.1016/j.suscom.2025.101154

Xiaoqian Meng, Yajie Zhao, Sijia Zheng, Zi Ye, Heping Wang

As microgrid systems become more complex and interconnected, traditional control strategies face significant challenges in terms of scalability, efficiency, and responsiveness. Existing models, often relying on time-triggered approaches, result in excessive communication, energy waste, and slower system responses. The main purpose of this work is to formulate a decentralized control architecture that communicates better, regulates voltage and frequency, and stabilizes the microgrids. To address these limitations, this research introduces an innovative decentralized control framework that combines Graph Neural Networks (GNNs) and Long Short-Term Memory (LSTM) networks, integrated with Event-Triggered Control to optimize microgrid operations. This methodology applies GNNs to capture the spatial dependencies among microgrid components like generators, storage, and loads. Meanwhile, the LSTMs identify the temporal dynamics associated with variations in load and generation. System control actions are then triggered only when necessary, hence reducing communication overhead considerably. The results demonstrates 55 % less communication load was reported, voltage regulation accuracy increased by 45 %, and other efficiency measures for frequency regulation improved by 35 %. Along with these, other performance metrics indicate a 30 % improvement of the Voltage Stability Index (VSI) going from 0.47 to 0.33 and lowering the Frequency Regulation Error (FRE) by 20 % from 4.5 % to 3.6 %. All of which consolidated the evidence of the efficiency of the approach suggested to control microgrid operations in a real-time adaptive energy-efficient manner. These findings highlight the powerful combination of GNNs and LSTMs for achieving adaptive, energy-efficient, and real-time control in decentralized microgrid systems.

随着微电网系统变得越来越复杂和互联，传统的控制策略在可扩展性、效率和响应性方面面临着重大挑战。现有的模型通常依赖于时间触发的方法，导致过度的通信、能源浪费和较慢的系统响应。本工作的主要目的是制定一个分散的控制架构，以更好地通信，调节电压和频率，并稳定微电网。为了解决这些限制，本研究引入了一种创新的分散控制框架，该框架结合了图神经网络（gnn）和长短期记忆（LSTM）网络，并与事件触发控制相结合，以优化微电网的运行。该方法应用gnn来捕获微电网组件（如发电机、存储和负载）之间的空间依赖关系。同时，lstm识别与负荷和发电量变化相关的时间动态。系统控制动作只在必要时触发，因此大大减少了通信开销。结果表明，通信负荷降低了55% %，电压调节精度提高了45% %，频率调节的其他效率措施提高了35% %。与此同时，其他性能指标表明，电压稳定指数（VSI）从0.47提高到0.33，提高了30 %，频率调节误差（FRE）从4.5 %降低到3.6 %，降低了20 %。所有这些都进一步证明了以实时自适应节能方式控制微电网运行的方法的有效性。这些发现强调了gnn和lstm的强大组合，可以在分散的微电网系统中实现自适应、节能和实时控制。

{"title":"Decentralized energy-efficient microgrid control Using Graph neural networks and LSTM-based Event-Triggered control","authors":"Xiaoqian Meng, Yajie Zhao, Sijia Zheng, Zi Ye, Heping Wang","doi":"10.1016/j.suscom.2025.101154","DOIUrl":"10.1016/j.suscom.2025.101154","url":null,"abstract":"<div><div>As microgrid systems become more complex and interconnected, traditional control strategies face significant challenges in terms of scalability, efficiency, and responsiveness. Existing models, often relying on time-triggered approaches, result in excessive communication, energy waste, and slower system responses. The main purpose of this work is to formulate a decentralized control architecture that communicates better, regulates voltage and frequency, and stabilizes the microgrids. To address these limitations, this research introduces an innovative decentralized control framework that combines Graph Neural Networks (GNNs) and Long Short-Term Memory (LSTM) networks, integrated with Event-Triggered Control to optimize microgrid operations. This methodology applies GNNs to capture the spatial dependencies among microgrid components like generators, storage, and loads. Meanwhile, the LSTMs identify the temporal dynamics associated with variations in load and generation. System control actions are then triggered only when necessary, hence reducing communication overhead considerably. The results demonstrates 55 % less communication load was reported, voltage regulation accuracy increased by 45 %, and other efficiency measures for frequency regulation improved by 35 %. Along with these, other performance metrics indicate a 30 % improvement of the Voltage Stability Index (VSI) going from 0.47 to 0.33 and lowering the Frequency Regulation Error (FRE) by 20 % from 4.5 % to 3.6 %. All of which consolidated the evidence of the efficiency of the approach suggested to control microgrid operations in a real-time adaptive energy-efficient manner. These findings highlight the powerful combination of GNNs and LSTMs for achieving adaptive, energy-efficient, and real-time control in decentralized microgrid systems.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101154"},"PeriodicalIF":3.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144479965","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