IET Smart Grid最新文献

Reinforcement Learning-Based Adaptation of Grid Following Inverter's Internal Controller to Networked Microgrids' Strengths 基于强化学习的电网跟随逆变器内控制器对网络化微电网强度的自适应

IF 2.7

IET Smart Grid Pub Date : 2025-10-17 DOI: 10.1049/stg2.70039

Thanh Long Vu, Monish Mukherjee, Ankit Singhal, Kevin Schneider, Wei Du, Nikolai Drigal, Francis Tuffner, Jing Xie

{"title":"Reinforcement Learning-Based Adaptation of Grid Following Inverter's Internal Controller to Networked Microgrids' Strengths","authors":"Thanh Long Vu, Monish Mukherjee, Ankit Singhal, Kevin Schneider, Wei Du, Nikolai Drigal, Francis Tuffner, Jing Xie","doi":"10.1049/stg2.70039","DOIUrl":"https://doi.org/10.1049/stg2.70039","url":null,"abstract":"The varying topological configurations, generator commitments and dispatches, and dynamic load demand lead to changing system's strengths during the operations of networked microgrids. When the system's strengths significantly change, the fixed control gains at large devices may result in unsatisfactory system performance; this necessitates the tuning of the control gains at large devices to adapt to the changing system's strengths. In this paper, observer-based reinforcement learning (RL) is utilised to automatically tune the proportional-integral (PI) gains of phase lock loop (PLL) controller of grid-following (GFL) inverters to adapt to the changing strengths of microgrids and networked microgrids. The RL agent in this framework augments an observer predicting system's strengths, from which the RL control policy will adjust accordingly to tune the PLL controller's gains towards the system's strengths. Also, to enhance the control performance, the recently introduced Barrier function-based RL framework is leveraged for the design of reward function to prevent the high frequency nadir. An operational 26 kV electric distribution system, which is modelled as networked microgrids, is used to illustrate the need and effectiveness of the proposed RL-tuned control.","PeriodicalId":36490,"journal":{"name":"IET Smart Grid","volume":"8 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/stg2.70039","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145317325","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Coordinated Optimal Dispatching Strategy for Photovoltaic-Storage-Charging Systems Considering Charging Services and Demand Response 考虑充电服务和需求响应的光伏-储能-充电系统协调优化调度策略

IF 2.7

IET Smart Grid Pub Date : 2025-10-13 DOI: 10.1049/stg2.70040

Zhichao Lin, Busheng Luo, Yingmin Wang, Xiangyang Su, Pengyu Zhang, Yuting Huang

{"title":"Coordinated Optimal Dispatching Strategy for Photovoltaic-Storage-Charging Systems Considering Charging Services and Demand Response","authors":"Zhichao Lin, Busheng Luo, Yingmin Wang, Xiangyang Su, Pengyu Zhang, Yuting Huang","doi":"10.1049/stg2.70040","DOIUrl":"https://doi.org/10.1049/stg2.70040","url":null,"abstract":"Photovoltaic-storage-charging (PSC) systems, beyond delivering electric vehicle (EV) charging services, exhibit certain degrees of load flexibility, thereby enabling their participation in demand response (DR) markets. An optimal scheduling strategy for PSC systems that accounts for the coupled constraints between charging services and the DR market has been proposed in this paper. First, the inherent characteristics of system resources have been analysed, and mathematical models for both charging services and demand response have been developed. Then, a unified framework is constructed based on the concept of callable capacity, capturing the coupling relationship between the two service types. An optimisation model is formulated with the objective of maximising total system profit, while incorporating constraints such as market participation rules, baseline load definitions, and system operation limits. The callable capacities associated with different service mechanisms are treated as control variables to enable optimal dispatching of the system across both charging and demand response services. Finally, the effectiveness of the proposed strategy is validated through a case study of a real-world PSC system.","PeriodicalId":36490,"journal":{"name":"IET Smart Grid","volume":"8 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/stg2.70040","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145316905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Temperature Equalisation Control Method for DC-DC Cascaded Energy Storage Systems Considering Temperature Trends 考虑温度趋势的DC-DC级联储能系统温度均衡控制方法

IF 2.7

IET Smart Grid Pub Date : 2025-10-08 DOI: 10.1049/stg2.70037

Shixian Bai, Xiangqian Tong, Jie Zhou, Hanqing Zhao

{"title":"Temperature Equalisation Control Method for DC-DC Cascaded Energy Storage Systems Considering Temperature Trends","authors":"Shixian Bai, Xiangqian Tong, Jie Zhou, Hanqing Zhao","doi":"10.1049/stg2.70037","DOIUrl":"https://doi.org/10.1049/stg2.70037","url":null,"abstract":"The battery is a critical component in electrochemical energy storage systems. High temperatures can accelerate battery degradation and create safety risks, such as thermal failure. Thus, effective heat dissipation is essential to reduce the operating temperature, extend battery life and minimise thermal failure risks. Maintaining a low-temperature differential among batteries also improves system efficiency and economic performance. This study proposes a cascaded DC-DC energy storage system that maintains battery temperature equilibrium based on module temperature trends and reduces temperature differences by distributing power across individual DC-DC converters. First, this study investigates the heat dissipation technology of energy storage batteries. Second, to enhance the speed of temperature homogenisation, a temperature trend forecasting the equalisation control method is introduced, building upon the average temperature equalisation and positive half-range temperature difference equalisation strategies. Finally, an experimental verification is conducted on a cascaded energy storage system consisting of eight DC-DC converters with a rated power of 11.6 kW. The results indicate that during charging, the temperature difference among battery cells remains below 2°C, whereas during discharging, the temperature difference is maintained below 1°C. Overall, temperature equalisation control based on cell temperature trend prediction demonstrates excellent performance in terms of both equalisation speed and effectiveness.","PeriodicalId":36490,"journal":{"name":"IET Smart Grid","volume":"8 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/stg2.70037","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145272170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An Adaptive Simplified Travelling Wave-Based Fault Detection, Classification and Location Estimation Strategy for Series Compensated Transmission Lines 基于自适应简化行波的串联补偿输电线路故障检测、分类与定位策略

IF 2.7

IET Smart Grid Pub Date : 2025-10-08 DOI: 10.1049/stg2.70041

Ehsan Akbari, Milad Samady Shadlu

{"title":"An Adaptive Simplified Travelling Wave-Based Fault Detection, Classification and Location Estimation Strategy for Series Compensated Transmission Lines","authors":"Ehsan Akbari, Milad Samady Shadlu","doi":"10.1049/stg2.70041","DOIUrl":"https://doi.org/10.1049/stg2.70041","url":null,"abstract":"Faults in power transmission systems pose significant challenges due to the complexity and length of transmission lines. Effective fault detection, classification and location are essential for preventing further damage to the power grid. While travelling wave-based algorithms are commonly used for fault location, they often focus on identifying the fault's location without classifying the fault type. Accurate classification is crucial for enabling efficient and timely responses from protection systems. This paper introduces an integrated model for fault detection, classification and location using voltage signals from a single terminal of a series-compensated transmission line with a static synchronous series compensator (SSSC). The Gabor Transform (GT) is utilised for feature extraction, enabling both fault detection and classification. Travelling wave theory is then applied to identify the faulty segment and estimate the fault location. Additionally, a novel technique adaptively calculates the threshold value during the protection algorithm's execution. The proposed method is validated through a comprehensive analysis of various fault scenarios and sensitivity analysis. Numerical simulations in MATLAB/Simulink show that the model achieves 100% accuracy for fault detection, classification, and faulty segment identification, with 99.7925% accuracy for fault location estimation, demonstrating its effectiveness in fault management.","PeriodicalId":36490,"journal":{"name":"IET Smart Grid","volume":"8 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/stg2.70041","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145271963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Cost-Effective NILM Solution With Three-Point Labelling and Non-Causal Convolution Technique 一个具有三点标记和非因果卷积技术的高性价比NILM解决方案

IF 2.7

IET Smart Grid Pub Date : 2025-09-24 DOI: 10.1049/stg2.70036

Yanan Zhang, Gan Zhou, Yanjun Feng, Zhan Liu, Li Huang, Zhi Li, Rui Bo

{"title":"A Cost-Effective NILM Solution With Three-Point Labelling and Non-Causal Convolution Technique","authors":"Yanan Zhang, Gan Zhou, Yanjun Feng, Zhan Liu, Li Huang, Zhi Li, Rui Bo","doi":"10.1049/stg2.70036","DOIUrl":"https://doi.org/10.1049/stg2.70036","url":null,"abstract":"Although deep learning is increasingly promising in the field of Non-Intrusive Load Monitoring (NILM) these days, the high costs of data recording and labelling represent a significant challenge for the training of supervised models. To address this, a cost-effective sequence-to-points NILM solution is proposed, integrating three-point labelling with non-causal convolution techniques. The approach introduces a semi-automatic labelling framework for obtaining NILM three-point data, which provides a low-cost data collection and labelling solution for large-scale applications. Then, a novel loss function combining coordinate loss and confidence loss is developed to address the positional misalignment and negative sample confusion in sequence-to-points scenario in NILM. Furthermore, an advanced neural network architecture based on multi-scale non-causal temporal convolution techniques is designed to capture unique features and operational modes of different appliances. Experimental results on the UK-DALE dataset show that the proposed mixed loss function has an advantage over plain Mean Absolute Error (MAE) on the sequence-to-points occasion, and the novel network outperforms on all of the appliances, demonstrating its potential for practical NILM applications.","PeriodicalId":36490,"journal":{"name":"IET Smart Grid","volume":"8 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/stg2.70036","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145146322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Secure Data Aggregation Scheme to Traceback Malicious Charging Piles for Large-Scale V2G Data-Sharing Scenarios 大规模V2G数据共享场景下恶意充电桩溯源的安全数据聚合方案

IF 2.7

IET Smart Grid Pub Date : 2025-09-07 DOI: 10.1049/stg2.70033

Nan Zhang, Di Liu, Yuhang Liu, Zhi Li, Jingyang Wang, Fusheng Lan, Wei Liang

{"title":"A Secure Data Aggregation Scheme to Traceback Malicious Charging Piles for Large-Scale V2G Data-Sharing Scenarios","authors":"Nan Zhang, Di Liu, Yuhang Liu, Zhi Li, Jingyang Wang, Fusheng Lan, Wei Liang","doi":"10.1049/stg2.70033","DOIUrl":"10.1049/stg2.70033","url":null,"abstract":"In large-scale vehicle-to-grid (V2G) data-sharing scenarios, the secure and accurate aggregation of data from charging piles is crucial to optimise orderly charging services for electric vehicles (EVs) and to support demand response or load forecasting. Existing data aggregation schemes often fail to detect outlier sharing-data sent by charging piles compromised by false data injection (FDI) attacks. To address this, we propose a lightweight secure data aggregation scheme that integrates node-level malicious charging piles traceback and isolation with distributed EC-ElGamal encryption. First, charging piles use the Hellinger-distance of shared charging data between adjacent charging cycles to judge whether the piles are malicious, and through iterative row/column cyclic shift operations, every malicious pile is tracebacked and excluded into a single designated group. Second, distributed key shares create a group public key while each pile retains its own secret key, enabling node-level distributed decryption of the aggregated ciphertext via lightweight EC-ElGamal addition and a single Pollard-lambda lookup. Experiments on 18,061 UrbanEV charging piles demonstrate an 81.7%–100% malicious piles excluding ratio, linear convergence (≈0.07 iterations per added pile), and security analysis proves that the proposed scheme has ECDDH anonymity, collusion resistance and differential-privacy immunity.","PeriodicalId":36490,"journal":{"name":"IET Smart Grid","volume":"8 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/stg2.70033","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145012180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cost-Effective Micro-Phasor Measurement Unit Placement in Radial Distribution Networks Using Adaptive Oppositional Artificial Rabbit Optimisation 基于自适应对偶人工兔子优化的径向配电网微相量测量单元成本效益配置

IF 2.7

IET Smart Grid Pub Date : 2025-09-05 DOI: 10.1049/stg2.70034

Nida Khanam, Mohd Rihan, Salman Hameed

{"title":"Cost-Effective Micro-Phasor Measurement Unit Placement in Radial Distribution Networks Using Adaptive Oppositional Artificial Rabbit Optimisation","authors":"Nida Khanam, Mohd Rihan, Salman Hameed","doi":"10.1049/stg2.70034","DOIUrl":"10.1049/stg2.70034","url":null,"abstract":"Ensuring cost-effective and reliable observability in power distribution networks is essential for the efficient operation of emerging smart grids. Micro-Phasor Measurement Units (μPMUs) offer high-resolution monitoring but incur significant installation costs, hindering widespread adoption. This paper provides an efficient and cost-effective μPMU deployment mechanism that ensures full topological observability. The suggested approach is tested on conventional IEEE 33-bus, 69-bus and 123-bus distribution test systems, with four different placement scenarios investigated to assess various cost-performance trade-offs. The proposed technique significantly reduces the required amount of μPMUs while maintaining full observability. The IEEE 33-bus system reduces μPMU count from 17 to 10, resulting in a 45.8% cost reduction. The 69-bus and 123-bus systems achieve cost savings of 27.1% and 30.5%, respectively. These findings illustrate the method's scalability and efficiency in reducing deployment costs while maintaining network observability. In addition to offering a useful tool for distribution network operators for planning real-time monitoring with low-cost sensing devices, the study assesses different solution scenarios (Cases I–IV) to demonstrate trade-offs. Although the focus is on a single-objective approach—minimising μPMU installation costs under complete observability constraints—it also gives comparative insights to aid planning decisions across multiple cost-performance situations.","PeriodicalId":36490,"journal":{"name":"IET Smart Grid","volume":"8 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/stg2.70034","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144990705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fault Identification Method of Distribution Networks Considering Multiple Disturbance Factors and Travelling Wave Transmission Characteristics 考虑多干扰因素和行波传输特性的配电网故障识别方法

IF 2.7

IET Smart Grid Pub Date : 2025-08-24 DOI: 10.1049/stg2.70029

Xinhai Li, Weiping Liao, Weiping Wang, Aihui Wen, Kun Yu

{"title":"Fault Identification Method of Distribution Networks Considering Multiple Disturbance Factors and Travelling Wave Transmission Characteristics","authors":"Xinhai Li, Weiping Liao, Weiping Wang, Aihui Wen, Kun Yu","doi":"10.1049/stg2.70029","DOIUrl":"10.1049/stg2.70029","url":null,"abstract":"In the context of increasingly complex distribution networks where accurate fault identification is vital for power supply reliability, conventional denoising methods face significant challenges, including information loss under multi-disturbance conditions and inadequate characterisation of weak faults due to insufficient feature saliency. To address these issues, this study proposes a novel fault identification methodology that comprehensively considers multi-disturbance factors and leverages travelling wave (TW) propagation characteristics. The proposed method uses adaptive local iterative filtering integrated—singular spectrum analysis (ALIF-SSA) for signal denoising, preserving essential fault information while suppressing noise, and extracts spectral features from reconstructed signals via frequency-domain transformation, focusing on harmonic distributions and dominant frequency components. A dual-band evaluation strategy (10–100 kHz and 1–5 MHz) is employed to enhance feature separability in interference-intensive environments, prioritising low-frequency components (10–100 kHz) for detection due to their stable transmission properties and analysing high-frequency components (1–5 MHz) through normalised amplitude ratio comparisons. This framework combines the stability of low-frequency signals with the discriminative resolution of high-frequency components for complementary diagnostics. Comparative case studies validate that the proposed approach outperforms conventional single-criterion methods in identification accuracy, offering a more reliable solution for fault identification in distribution networks.","PeriodicalId":36490,"journal":{"name":"IET Smart Grid","volume":"8 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/stg2.70029","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144894326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Market-Driven Approach to Congestion Management: Leveraging Cross-Grid Flexibility in Distribution Networks 市场驱动的拥塞管理方法：在配电网中利用跨电网的灵活性

IF 2.7

IET Smart Grid Pub Date : 2025-08-22 DOI: 10.1049/stg2.70032

Reza Khodabakhsh, Amir Zanj, Md Apel Mahmud

{"title":"A Market-Driven Approach to Congestion Management: Leveraging Cross-Grid Flexibility in Distribution Networks","authors":"Reza Khodabakhsh, Amir Zanj, Md Apel Mahmud","doi":"10.1049/stg2.70032","DOIUrl":"10.1049/stg2.70032","url":null,"abstract":"The rapid integration of renewable energy sources and the electrification of key sectors have significantly increased congestion challenges in power distribution networks. Traditional grid reinforcement strategies are often costly and time-consuming, necessitating the adoption of more flexible, market-based solutions. This paper introduces the OpenFlex market, a novel local flexibility market structure designed to enhance congestion management by incorporating cross-grid flexibility resources. The proposed framework enables Distribution System Operators (DSOs) to procure flexibility services beyond their local network, improving cost efficiency and system resilience. By leveraging the Inter-Grid Load Transfer Coordinator (IGLTC), the model facilitates optimal load transfers, minimises network losses, and enhances voltage stability. A case study demonstrates the effectiveness of the framework under various operational scenarios, highlighting its potential for reducing congestion management costs while ensuring grid reliability. Although DSO-level local flexibility markets are still at the pilot stage, the proposed framework extends these concepts by enabling cross-grid flexibility trading and coordinated congestion management, aligning with emerging regulatory trends. The results underscore the importance of regulatory support for cross-grid flexibility integration and suggest future directions for real-time flexibility trading and digital optimisation techniques.","PeriodicalId":36490,"journal":{"name":"IET Smart Grid","volume":"8 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/stg2.70032","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on Regional Power Grid Scheduling Strategy With Flexible Resource Clusters Based on Multi-Agent Deep Reinforcement Learning 基于多智能体深度强化学习的柔性资源集群区域电网调度策略研究

IF 2.7

IET Smart Grid Pub Date : 2025-08-19 DOI: 10.1049/stg2.70028

Gao Guanzhong, Yaping Li, Shengchun Yang, Jiahao Yan, Kedong Zhu, Jianguo Yao, Wenbo Mao

{"title":"Research on Regional Power Grid Scheduling Strategy With Flexible Resource Clusters Based on Multi-Agent Deep Reinforcement Learning","authors":"Gao Guanzhong, Yaping Li, Shengchun Yang, Jiahao Yan, Kedong Zhu, Jianguo Yao, Wenbo Mao","doi":"10.1049/stg2.70028","DOIUrl":"10.1049/stg2.70028","url":null,"abstract":"The increasing integration of distributed energy resources, controllable loads and energy storage systems is reshaping power systems by enhancing flexibility in supply–demand balancing. However, their large-scale deployment imposes significant communication and computational burdens on dispatch centres. Traditional model-driven scheduling methods often struggle to maintain efficiency and fairness among stakeholders, whereas existing deep reinforcement learning approaches lack mechanisms to address real-time response deviations within resource clusters leading to unstable policy performance. To tackle these challenges, this paper proposes a real-time scheduling strategy for partitioned power grids based on multi-agent deep reinforcement learning. A hierarchical distributed control framework is developed, where different agents manage regional grids and coordinate decision-making across flexible resource clusters. The framework adopts centralised training and distributed execution integrating real-time regulation performance as a regularisation term in agent rewards to improve learning stability and decision efficiency. Simulation results under varying renewable energy penetration levels demonstrate that the proposed method enhances scheduling performance and system robustness. This approach provides a promising solution for managing large-scale flexible resources and contributes to the intelligent operation of new type power systems.","PeriodicalId":36490,"journal":{"name":"IET Smart Grid","volume":"8 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/stg2.70028","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144869714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0