With integration of large-scale renewable energy, new controllable devices, and required reinforcement of power grids, modern power systems have typical characteristics such as uncertainty, vulnerability and openness, which makes operation and control of power grids face severe security challenges. Application of artificial intelligence (AI) technologies represented by machine learning in power grid regulation is limited by reliability, interpretability and generalization ability of complex modeling. Mode of hybrid-augmented intelligence (HAI) based on human-machine collaboration (HMC) is a pivotal direction for future development of AI technology in this field. Based on characteristics of applications in power grid regulation, this paper discusses system architecture and key technologies of human-machine hybrid-augmented intelligence (HHI) system for large-scale power grid dispatching and control (PGDC). First, theory and application scenarios of HHI are introduced and analyzed; then physical and functional architectures of HHI system and human-machine collaborative regulation process are proposed. Key technologies are discussed to achieve a thorough integration of human/machine intelligence. Finally, state-of-the-art and future development of HHI in power grid regulation are summarized, aiming to efficiently improve the intelligent level of power grid regulation in a human-machine interactive and collaborative way.
{"title":"Framework and Key Technologies of Human-machine Hybrid-augmented Intelligence System for Large-scale Power Grid Dispatching and Control","authors":"Shixiong Fan;Jianbo Guo;Shicong Ma;Lixin Li;Guozheng Wang;Haotian Xu;Jin Yang;Zening Zhao","doi":"10.17775/CSEEJPES.2023.00940","DOIUrl":"https://doi.org/10.17775/CSEEJPES.2023.00940","url":null,"abstract":"With integration of large-scale renewable energy, new controllable devices, and required reinforcement of power grids, modern power systems have typical characteristics such as uncertainty, vulnerability and openness, which makes operation and control of power grids face severe security challenges. Application of artificial intelligence (AI) technologies represented by machine learning in power grid regulation is limited by reliability, interpretability and generalization ability of complex modeling. Mode of hybrid-augmented intelligence (HAI) based on human-machine collaboration (HMC) is a pivotal direction for future development of AI technology in this field. Based on characteristics of applications in power grid regulation, this paper discusses system architecture and key technologies of human-machine hybrid-augmented intelligence (HHI) system for large-scale power grid dispatching and control (PGDC). First, theory and application scenarios of HHI are introduced and analyzed; then physical and functional architectures of HHI system and human-machine collaborative regulation process are proposed. Key technologies are discussed to achieve a thorough integration of human/machine intelligence. Finally, state-of-the-art and future development of HHI in power grid regulation are summarized, aiming to efficiently improve the intelligent level of power grid regulation in a human-machine interactive and collaborative way.","PeriodicalId":10729,"journal":{"name":"CSEE Journal of Power and Energy Systems","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10375976","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139695072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-28DOI: 10.17775/CSEEJPES.2023.01280
Zexin Zhao;Weijiang Chen;Zhichang Yang;Guoliang Zhao;Bin Han;Yunfei Xu;Nianwen Xiang;Shulai Wang
The modular multilevel matrix converter (M3C) is a potential frequency converter for low-frequency AC transmission. However, capacitor voltage control of high-voltage and large-capacity M3C is more difficult, especially for voltage balancing between branches. To solve this problem, this paper defines sequence circulating components and theoretically analyzes the influence mechanism of different sequence circulating components on branch capacitor voltage. A fully decoupled branch energy balancing control method based on four groups of sequence circulating components is proposed. This method can control capacitor voltages of nine branches in horizontal, vertical and diagonal directions. Considering influences of both circulating current and voltage, a cross decoupled control is designed to improve control precision. Simulation results are taken from a low-frequency transmission system based on PSCAD/EMTDC, and effectiveness and precision of the proposed branch energy balancing control method are verified in the case of nonuniform parameters and an unbalanced power system.
{"title":"Fully Decoupled Branch Energy Balancing Control Method for Modular Multilevel Matrix Converter Based on Sequence Circulating Components","authors":"Zexin Zhao;Weijiang Chen;Zhichang Yang;Guoliang Zhao;Bin Han;Yunfei Xu;Nianwen Xiang;Shulai Wang","doi":"10.17775/CSEEJPES.2023.01280","DOIUrl":"https://doi.org/10.17775/CSEEJPES.2023.01280","url":null,"abstract":"The modular multilevel matrix converter (M3C) is a potential frequency converter for low-frequency AC transmission. However, capacitor voltage control of high-voltage and large-capacity M3C is more difficult, especially for voltage balancing between branches. To solve this problem, this paper defines sequence circulating components and theoretically analyzes the influence mechanism of different sequence circulating components on branch capacitor voltage. A fully decoupled branch energy balancing control method based on four groups of sequence circulating components is proposed. This method can control capacitor voltages of nine branches in horizontal, vertical and diagonal directions. Considering influences of both circulating current and voltage, a cross decoupled control is designed to improve control precision. Simulation results are taken from a low-frequency transmission system based on PSCAD/EMTDC, and effectiveness and precision of the proposed branch energy balancing control method are verified in the case of nonuniform parameters and an unbalanced power system.","PeriodicalId":10729,"journal":{"name":"CSEE Journal of Power and Energy Systems","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10375968","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139694897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-28DOI: 10.17775/CSEEJPES.2023.05850
Jinliang He;Zhifei Han;Jun Hu
The ubiquitous power Internet of Things (UPIoT) uses modern information technology and advanced communication technologies to realize interconnection and human-computer interaction in all aspects of the power system. UPIoT has the characteristics of comprehensive state perception and efficient information processing, and has broad application prospects for transformation of the energy industry. The fundamental facility of the UPIoT is the sensor-based information network. By using advanced sensors, Wireless Sensor Networks (WSNs), and advanced data processing technologies, Internet of Things can be realized in the power system. In this paper, a framework of WSNs based on advanced sensors towards UPIoT is proposed. In addition, the most advanced sensors for UPIoT purposes are reviewed, along with an explanation of how the sensor data obtained in UPIoT is utilized in various scenarios.
{"title":"Advanced Sensors Towards Ubiquitous Power Internet of Things","authors":"Jinliang He;Zhifei Han;Jun Hu","doi":"10.17775/CSEEJPES.2023.05850","DOIUrl":"https://doi.org/10.17775/CSEEJPES.2023.05850","url":null,"abstract":"The ubiquitous power Internet of Things (UPIoT) uses modern information technology and advanced communication technologies to realize interconnection and human-computer interaction in all aspects of the power system. UPIoT has the characteristics of comprehensive state perception and efficient information processing, and has broad application prospects for transformation of the energy industry. The fundamental facility of the UPIoT is the sensor-based information network. By using advanced sensors, Wireless Sensor Networks (WSNs), and advanced data processing technologies, Internet of Things can be realized in the power system. In this paper, a framework of WSNs based on advanced sensors towards UPIoT is proposed. In addition, the most advanced sensors for UPIoT purposes are reviewed, along with an explanation of how the sensor data obtained in UPIoT is utilized in various scenarios.","PeriodicalId":10729,"journal":{"name":"CSEE Journal of Power and Energy Systems","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10375971","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141304111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-28DOI: 10.17775/CSEEJPES.2023.05970
Yonghua Song;Ge Chen;Hongcai Zhang
Transition towards carbon-neutral power systems has necessitated optimization of power dispatch in active distribution networks (ADNs) to facilitate integration of distributed renewable generation. Due to unavailability of network topology and line impedance in many distribution networks, physical model-based methods may not be applicable to their operations. To tackle this challenge, some studies have proposed constraint learning, which replicates physical models by training a neural network to evaluate feasibility of a decision (i.e., whether a decision satisfies all critical constraints or not). To ensure accuracy of this trained neural network, training set should contain sufficient feasible and infeasible samples. However, since ADNs are mostly operated in a normal status, only very few historical samples are infeasible. Thus, the historical dataset is highly imbalanced, which poses a significant obstacle to neural network training. To address this issue, we propose an enhanced constraint learning method. First, it leverages constraint learning to train a neural network as surrogate of ADN's model. Then, it introduces Synthetic Minority Oversampling Technique to generate infeasible samples to mitigate imbalance of historical dataset. By incorporating historical and synthetic samples into the training set, we can significantly improve accuracy of neural network. Furthermore, we establish a trust region to constrain and thereafter enhance reliability of the solution. Simulations confirm the benefits of the proposed method in achieving desirable optimality and feasibility while maintaining low computational complexity.
{"title":"Constraint Learning-based Optimal Power Dispatch for Active Distribution Networks with Extremely Imbalanced Data","authors":"Yonghua Song;Ge Chen;Hongcai Zhang","doi":"10.17775/CSEEJPES.2023.05970","DOIUrl":"https://doi.org/10.17775/CSEEJPES.2023.05970","url":null,"abstract":"Transition towards carbon-neutral power systems has necessitated optimization of power dispatch in active distribution networks (ADNs) to facilitate integration of distributed renewable generation. Due to unavailability of network topology and line impedance in many distribution networks, physical model-based methods may not be applicable to their operations. To tackle this challenge, some studies have proposed constraint learning, which replicates physical models by training a neural network to evaluate feasibility of a decision (i.e., whether a decision satisfies all critical constraints or not). To ensure accuracy of this trained neural network, training set should contain sufficient feasible and infeasible samples. However, since ADNs are mostly operated in a normal status, only very few historical samples are infeasible. Thus, the historical dataset is highly imbalanced, which poses a significant obstacle to neural network training. To address this issue, we propose an enhanced constraint learning method. First, it leverages constraint learning to train a neural network as surrogate of ADN's model. Then, it introduces Synthetic Minority Oversampling Technique to generate infeasible samples to mitigate imbalance of historical dataset. By incorporating historical and synthetic samples into the training set, we can significantly improve accuracy of neural network. Furthermore, we establish a trust region to constrain and thereafter enhance reliability of the solution. Simulations confirm the benefits of the proposed method in achieving desirable optimality and feasibility while maintaining low computational complexity.","PeriodicalId":10729,"journal":{"name":"CSEE Journal of Power and Energy Systems","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10375977","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139695118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The complexity and uncertainty in power systems cause great challenges to controlling power grids. As a popular data-driven technique, deep reinforcement learning (DRL) attracts attention in the control of power grids. However, DRL has some inherent drawbacks in terms of data efficiency and explainability. This paper presents a novel hierarchical task planning (HTP) approach, bridging planning and DRL, to the task of power line flow regulation. First, we introduce a three-level task hierarchy to model the task and model the sequence of task units on each level as a task planning-Markov decision processes (TP-MDPs). Second, we model the task as a sequential decision-making problem and introduce a higher planner and a lower planner in HTP to handle different levels of task units. In addition, we introduce a two-layer knowledge graph that can update dynamically during the planning procedure to assist HTP. Experimental results conducted on the IEEE 118-bus and IEEE 300-bus systems demonstrate our HTP approach outperforms proximal policy optimization, a state-of-the-art deep reinforcement learning (DRL) approach, improving efficiency by 26.16% and 6.86% on both systems.
{"title":"Hierarchical Task Planning for Power Line Flow Regulation","authors":"Chenxi Wang;Youtian Du;Yanhao Huang;Yuanlin Chang;Zihao Guo","doi":"10.17775/CSEEJPES.2023.00620","DOIUrl":"https://doi.org/10.17775/CSEEJPES.2023.00620","url":null,"abstract":"The complexity and uncertainty in power systems cause great challenges to controlling power grids. As a popular data-driven technique, deep reinforcement learning (DRL) attracts attention in the control of power grids. However, DRL has some inherent drawbacks in terms of data efficiency and explainability. This paper presents a novel hierarchical task planning (HTP) approach, bridging planning and DRL, to the task of power line flow regulation. First, we introduce a three-level task hierarchy to model the task and model the sequence of task units on each level as a task planning-Markov decision processes (TP-MDPs). Second, we model the task as a sequential decision-making problem and introduce a higher planner and a lower planner in HTP to handle different levels of task units. In addition, we introduce a two-layer knowledge graph that can update dynamically during the planning procedure to assist HTP. Experimental results conducted on the IEEE 118-bus and IEEE 300-bus systems demonstrate our HTP approach outperforms proximal policy optimization, a state-of-the-art deep reinforcement learning (DRL) approach, improving efficiency by 26.16% and 6.86% on both systems.","PeriodicalId":10729,"journal":{"name":"CSEE Journal of Power and Energy Systems","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10375975","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139695065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}