Article
Engineering, Electrical & Electronic
Tingyu Jiang, Ping Ju, Chong Wang, Hongyu Li, Jingzi Liu
Summary: The article presents a coordinated control strategy for frequency regulation using inverter air-conditioning units for primary frequency regulation and fixed frequency air-conditioning units for secondary frequency regulation. Random triggering and recovery methods are proposed for stable regulation, along with constant equivalent duty ratio and transforming time interval methods to maintain regulation power stability. Additionally, a recovery method is suggested for mitigating power rebound after regulation.
IEEE TRANSACTIONS ON SMART GRID
(2021)
Article
Energy & Fuels
Jiawen Li, Tao Yu, Xiaoshun Zhang
Summary: A coordinated power control framework and a novel deep reinforcement learning algorithm EIC-MADDPG are proposed to achieve coordinated control and improve performance in a multi-area integrated energy system (IES). By combining imitation learning and curriculum learning, the algorithm can adaptively derive optimal coordinated control strategies for multiple LFC controllers.
Article
Telecommunications
Siguang Chen, Bei Tang, Kun Wang
Summary: In this paper, an efficient and intelligent computation offloading mechanism with resource allocation is studied for the randomness distribution of multiple users in the dynamic large-scale IoT scenario. An optimization problem is formulated to minimize the total energy consumption of all tasks, and a TD3PG-ICO algorithm is proposed to solve this problem. The simulation results show that the proposed algorithm has faster convergence speed and good robustness, with the ability to reduce total energy consumption compared to other schemes.
DIGITAL COMMUNICATIONS AND NETWORKS
(2023)
Article
Chemistry, Physical
Jiawen Li, Tao Yu, Bo Yang
Summary: An intelligent control framework is proposed for coordinating the air and hydrogen supply systems in PEMFCs, using ensemble imitation learning and multi-trick deep deterministic policy gradient approach to enhance exploration efficiency. Multiple reinforcement learning explorers and control algorithm explorers are utilized to address sparse rewards and improve training efficiency. Multiple tricks are applied to improve the overestimated Q value, resulting in a model-free intelligent control algorithm with better global searching ability.
INTERNATIONAL JOURNAL OF HYDROGEN ENERGY
(2021)
Article
Energy & Fuels
Qiushi Cui, Gyoungjae Kim, Yang Weng
Summary: This study aims to address damping control issues under unknown latency in power networks by redesigning the learning structure and developing a new method. Proposed novel reward algorithm optimizes system stability and reliability by considering various factors.
Article
Computer Science, Information Systems
Wei Chen, Wenbin Yang, Haifeng Qi, Zhaohui Shi, Hua Geng
Summary: With higher wind power penetration, the power system faces challenges in active power balance and system frequency regulation. This paper proposes a coordinated power reserve control method for wind farms to participate in frequency regulation. By using linear programming, the method maximizes the kinetic energy and minimizes the blade pitch action of wind turbine generators to allocate power reserves. The results of case studies validate the effectiveness of the proposed method in improving the frequency regulation ability of wind farms.
Article
Engineering, Electrical & Electronic
Daisuke Terazono, Jia Liu, Yushi Miura, Shigekazu Sakabe, Hassan Bevrani, Toshifumi Ise
Summary: This article introduces a new control scheme utilizing kinetic energy storage to provide frequency regulation support for the power grid and reduce sensitivity to grid voltage imbalance and distortion. The proposed coordinated control between VSG control and motor speed control offers faster frequency support response compared to previous schemes based on frequency measurement.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2021)
Article
Energy & Fuels
Slimane Sadoudi, Mohamed Boudour, Nour El Yakine Kouba
Summary: This paper discusses optimal multi-stage power management, control, and load shedding coordination in interconnected microgrids with various renewable energy sources. It introduces hybrid energy storage systems, flexible AC transmission systems, and an artificial intelligence strategy combining a fuzzy-proportional-integral-derivative controller with filter. The proposed control strategy shows good performance in managing and controlling microgrid power under renewable energy integration and load disturbances scenarios.
INTERNATIONAL JOURNAL OF ENERGY RESEARCH
(2021)
Article
Energy & Fuels
Arman Oshnoei, Morteza Kheradmandi, Frede Blaabjerg, Nikos D. Hatziargyriou, S. M. Muyeen, Amjad Anvari-Moghaddam
Summary: This paper proposes a coordinated control strategy for load frequency control in a Virtual Power Plant (VPP). The strategy considers distributed Battery Energy Storage Systems (BESSs) and Heat Pump Water Heaters (HPWHs) as part of the VPP. The optimization framework takes into account dynamic regulation performance and total regulation cost, and a fuzzy strategy is used to determine the final solution. The regulation signal of the VPP is dispatched based on the speed and available power capacity of its components.
Article
Computer Science, Information Systems
Yangyang Hou, Huajie Hong, Zhaomei Sun, Dasheng Xu, Zhe Zeng
Summary: This paper explores the application of deep reinforcement learning in the learning of motion ability of manipulators and introduces methods to suppress the overestimation bias of values, improving the learning ability of manipulators. By optimizing the reward function and experience replay, the learning efficiency of manipulators is enhanced.
Article
Green & Sustainable Science & Technology
Yahui Du, Zhihua Zhou, Jing Zhao
Summary: With the increasing refinement of building functions and regions, researchers have proposed a regulation model that dynamically adjusts the set point temperature in different areas to reduce energy load and improve energy efficiency. Experimental results show that this strategy can reduce load demand by about 6.16% without sacrificing indoor comfort. Further optimization and control strategies can achieve overall energy savings of 12.78% for HVAC systems.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Energy & Fuels
Ji Han, Shihong Miao, Zhe Chen, Zhou Liu, Yaowang Li, Weichen Yang, Ziwen Liu
Summary: This paper proposes a coordinated control framework for wind farms and adiabatic compressed air energy storage stations to balance power fluctuations, achieving improved system frequency nadirs. The three-level control method effectively distributes frequency regulation power and enhances system frequency nadirs across different wind power and A-CAES capacities.
Article
Engineering, Electrical & Electronic
Sai Xu, Chen Chen, Yanan Du, Jiangzhou Wang, Jie Zhang
Summary: This paper proposes an intelligent reflecting surface (IRS) backscatter based uplink coordinated transmission strategy for a radio cellular network. The aim is to maximize the weighted sum rate (WSR) under certain constraints by joint optimization of active beamforming at the power beacon (PB), passive beamforming at the IRSs and uplink user scheduling. The simulation results demonstrate the achievable WSR of the considered network.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2023)
Article
Green & Sustainable Science & Technology
Jiaming Chang, Yang Du, Eng Lim, Huiqing Wen, Xingshuo Li, Jiang Lin
Summary: This paper proposes a forecasting-based VIC (FB-VIC) and coordinated reserve strategy to utilize PVs as an alternative inertia supplier without using ESS. PV generation is pre-reserved based on solar forecasting results, either at PV plants about to be shaded for local curtailment or other unshaded PV plants providing virtual inertia. The coordinated reserve strategy determines how much to reserve at the selected PV plant, making the system more robust to forecasting errors.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2021)
Article
Computer Science, Interdisciplinary Applications
Tanuja Joshi, Shikhar Makker, Hariprasad Kodamana, Harikumar Kandath
Summary: Control of batch processes is a challenging task due to their complex dynamics and non-steady state operating conditions. Developing control strategies that directly interact with the process and learning from experiences can help address some of these challenges. The study introduces a novel actor-critic RL algorithm and demonstrates its efficacy in various batch process examples.
COMPUTERS & CHEMICAL ENGINEERING
(2021)
Article
Green & Sustainable Science & Technology
Jiawen Li, Shengchun Yang, Tao Yu, Xiaoshun Zhang
Summary: An advanced controller based on large-scale deep reinforcement learning is proposed for controlling the stack temperature of PEMFC, along with a new deep reinforcement learning algorithm named CGS-L4DPG. The inclusion of curriculum guidance strategy and imitation learning in the algorithm improves the performance and robustness of the controller, making it more effective in controlling the PEMFC stack temperature than existing control algorithms.
IET RENEWABLE POWER GENERATION
(2022)
Editorial Material
Energy & Fuels
Bo Yang, Dongran Song, Xing He, Xiaoshun Zhang, Sungyun Choi, Chao Duan, Yaxing Ren
FRONTIERS IN ENERGY RESEARCH
(2022)
Article
Thermodynamics
Xiaoshun Zhang, Tao Yu, Xiaoguang Ma, Lexin Guo
Summary: Given the significant energy loss caused by partial shading in photovoltaic systems, various array reconfiguration techniques have been proposed to improve power generation efficiency. Previous studies focused on maximizing power output without considering multi-period power fluctuations, resulting in low total profit. This paper presents a new multi-period photovoltaic array reconfiguration model with a hydrogen energy storage system under partial shading conditions, aiming to maximize total profit by considering electricity selling profit, hydrogen selling profit, and regulation cost. A novel multi-agent negotiation algorithm with an auctioneer and multiple bidders is designed to address this problem, achieving efficient and distributed optimization. Case studies demonstrate that the proposed algorithm outperforms five centralized meta-heuristic algorithms, significantly increasing total profit under varying partial shading conditions.
ENERGY CONVERSION AND MANAGEMENT
(2022)
Article
Energy & Fuels
Jiawen Li
Summary: This paper proposes a data-driven multi-objective energy coordinative management policy to enhance the net output power and efficiency of a solid oxide fuel cell (SOFC). The policy focuses on maintaining stable oxygen excess ratio (OER) and fuel utilization (FU) ratio while meeting load demand through optimization agent and controller design.
Article
Chemistry, Physical
Jiawen Li, Haoyang Cui, Wei Jiang, Hengwen Yu
Summary: To address the nonlinearity and constraints in solid oxide fuel cell (SOFC) control, a dual-model control framework (DMCF) is proposed, with a PID controller and a supplementary dynamic controller. The supplementary controller adapts to uncertainties and fuel utilization constraints, while an imitation distributed deep deterministic policy gradient (ID3PG) algorithm enhances the robustness and adaptive capacity. Simulation results demonstrate the effectiveness of the proposed framework in controlling SOFC output voltage and satisfying fuel utilization constraints.
INTERNATIONAL JOURNAL OF HYDROGEN ENERGY
(2023)
Article
Energy & Fuels
Hongbin Zhu, Xiang Gao, Lei Zhao, Xiaoshun Zhang
Summary: A novel bi-objective optimal wind farm energy capture (OWFEC) algorithm is proposed in this study, which considers both maximum power output and the balance of fatigue load distribution to reduce maintenance cost. To rapidly obtain high-quality Pareto optimal solutions, a decomposition-based multi-classifier-assisted evolutionary algorithm is designed. Simulations are carried out with three different scales of wind farms, and five familiar Pareto-based meta-heuristic algorithms are introduced for performance comparison to evaluate the effectiveness and performance of the proposed technique.
Article
Automation & Control Systems
Jiawen Li, Haoyang Cui, Wei Jiang
Summary: To maintain the net output power of solid oxide fuel cells (SOFC) and avoid violating oxygen excess ratio and fuel utilization constraints, a data-driven gas supply system coordination management method is proposed. The algorithm, called PE-MA4DPG, is based on population evolution and utilizes multi-agent double delay deep deterministic policy gradient. The algorithm's effectiveness is demonstrated in comparison to existing algorithms through three experiments.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Electrical & Electronic
Xiaoshun Zhang, Chuangzhi Li, Biao Xu, Zhenning Pan, Tao Yu
Summary: To balance power disturbances, an independent system operator (ISO) assigns power regulation commands to resources via AGC dispatch. This paper proposes a novel DDNN-TL for rapid approximation of high-quality Pareto optimal solutions in AGC dispatch. Training data is generated from Pareto optimal solutions obtained by various algorithms. DDNN parameters are updated through offline training with this data. The results demonstrate superior performance in optimization speed and stability compared to other algorithms.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2023)
Article
Energy & Fuels
Jiawen Li, Zhou Tao, Keke He, Hengwen Yu, Hongwei Du, Shuangyu Liu, Haoyang Cui
Summary: This paper presents a distributed area autonomy load frequency control (DAA-LFC) method that balances the interests of different grid operators and achieves fast frequency recovery. The method treats each area controller in a multiarea microgrid as an agent and uses gameplay for global optimization. The agents make independent decisions and do not need to communicate during online operation. In addition, a distributed quantum multiagent deep meta-deterministic policy gradient (DQMA-DMDPG) algorithm is proposed to achieve collaborative multitask learning. The simulation results show that the proposed method reduces frequency deviation, power generation costs, and balances the interests of multiple operators.
Article
Green & Sustainable Science & Technology
Jiawen Li, Tao Zhou
Summary: This paper addresses the challenge of active fault-tolerant coordination control for proton exchange membrane fuel cells (PEMFCs). The proposed method aims to stabilize the output performance of four operating variables and prevent constraint violations in PEMFCs during failure scenarios. The method utilizes a curriculum-based multiagent deep meta-deterministic policy gradient algorithm to achieve multitask collaboration and enhance PEMFC robustness. The algorithm consists of a meta-learner and a base learner, which cooperate to detect faults and select appropriate control policies.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2023)
Article
Computer Science, Information Systems
Jiawen Li, Tao Zhou
Summary: This article proposes a swarm intelligence load frequency control (SI-LFC) method for coordinating the interests of multiple operators in an isolated multiarea microgrid. The method treats the units in each area as independent agents and adopts swarm intelligence centralized offline learning policy to achieve a balance of interests. Online, each unit only needs to collect the frequency locally to achieve global optimal control, reducing network communication burden. The article also introduces an evolutionary multiagent deep meta-actor-critic (EMA-DMAC) algorithm, which enhances collaborative learning of swarm agents, improving the robustness and quality of SI-LFC strategies. The proposed method's effectiveness is demonstrated in a simulation of a four-area LFC model for Sansha island in the China Southern Grid (CSG).
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Energy & Fuels
Jiawen Li, Yuanyuan Cheng, Hengwen Yu, Hongwei Du, Haoyang Cui
Summary: This paper proposes a data-driven active fault-tolerant control method for stable control of proton exchange membrane fuel cells (PEMFCs) in the event of a fault. It combines meta-reinforcement learning with multiagent reinforcement learning to provide independent multitask cooperative learning capabilities, ensuring excellent robustness.
Article
Automation & Control Systems
Jiawen Li, Tao Zhou, Haoyang Cui
Summary: This paper proposes an active coordinated fault tolerance load frequency control (AFCT-LFC) method to prevent sudden frequency changes caused by unit actuator failures or unplanned decommissioning in a multi-area interconnected grid. It also introduces a brain-Inspired deep meta-deterministic policy gradient algorithm (BIMA-DMDPG) for multi-agent centralized training and distributed training. The method is tested in a four-area LFC model and shows superior performance compared to existing algorithms.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Construction & Building Technology
Jiawen Li, Tao Zhou
Summary: This study proposes a sea computing-based grid-area coordinated load frequency control method which effectively reduces frequency fluctuations and improves quality and robustness. By introducing meta-reinforcement learning and curriculum learning, the method guides agent training to obtain LFC strategies that suit market requirements.
SUSTAINABLE CITIES AND SOCIETY
(2023)
Article
Engineering, Electrical & Electronic
Wandry R. Faria, Gregorio Munoz-Delgado, Javier Contreras, Benvindo R. Pereira Jr
Summary: This paper proposes a new bilevel mathematical model for competitive electricity markets, taking into account the participation of distribution systems operators. A new pricing method is introduced as an alternative to the inaccessible dual variables of the transmission system.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2024)
Article
Engineering, Electrical & Electronic
Chao Zhang, Liwei Zhang, Dong Wang, Kaiyuan Lu
Summary: The load disturbance rejection ability of electrical machine systems is crucial in many applications. Existing studies mainly focus on improving disturbance observers, but the speed response control during the transient also plays a significant role. This paper proposes a sliding mode disturbance observer-based load disturbance rejection control with an adaptive filter and a Smith predictor-based speed filter delay compensator to enhance the transient speed response.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2024)
Article
Engineering, Electrical & Electronic
Arif Hussain, Arif Mehdi, Chul-Hwan Kim
Summary: The proposed scheme in this research paper is a communication-less islanding detection system based on recurrent neural network (RNN) for hybrid distributed generator (DG) systems. The scheme demonstrates good performance in feature extraction, feature selection, and islanding detection, and it also performs effectively in noisy environments.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2024)
Article
Engineering, Electrical & Electronic
Zonghui Sun, Xizheng Guo, Shinan Wang, Xiaojie You
Summary: This paper presents a status pre-matching method (SPM) that eliminates the iterative calculations for resistance switch model, and simulates all operation modes of PECs through a more convenient approach. Furthermore, a FPGA implementation scheme is proposed to fully utilize the multiplier units of FPGA.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2024)
Article
Engineering, Electrical & Electronic
Rui Zhou, Shuheng Chen, Yang Han, Qunying Liu, Zhe Chen, Weihao Hu
Summary: In power system scheduling with variable renewable energy sources, considering both spatial and temporal correlations is a challenging task due to the complex intertwining of spatiotemporal characteristics and computational complexity caused by high dimensionality. This paper proposes a novel probabilistic spatiotemporal scenario generation (PSTSG) method that generates probabilistic scenarios accounting for spatial and temporal correlations simultaneously. The method incorporates Latin hypercube sampling, copula-importance sampling theory, and probability-based scenario reduction technique to efficiently capture the spatial and temporal correlation in the dynamic optimal power flow problem. Numerical simulations demonstrate the superiority of the proposed approach in terms of computational efficiency and accuracy compared to existing methods.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2024)
Article
Engineering, Electrical & Electronic
Juan Manuel Mauricio, J. Carlos Olives-Camps, Jose Maria Maza-Ortega, Antonio Gomez-Exposito
Summary: This paper proposes a simplified thermal model of VSC, which can produce accurate results at a low computational cost. The model consists of a simple first-order thermal dynamics system and two quadratic equations to model power losses. A methodology is also provided to derive the model parameters from manufacturer data.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2024)
Article
Engineering, Electrical & Electronic
Jae-Kyeong Kim, Kyeon Hur
Summary: This paper investigates the relationship between the accuracy of finite difference-based trajectory sensitivity (FDTS) analysis and the perturbation size in non-smooth systems. The study reveals that the approximation accuracy is significantly influenced by the perturbation size, and linear approximation is the most suitable method for practical applications.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2024)
Article
Engineering, Electrical & Electronic
Yuan Si, Amjad Anvari-Moghaddam
Summary: This paper investigates the impact of geomagnetic disturbances on small signal stability in power systems and proposes the installation of blocking devices to mitigate the negative effects. Quantitative evaluation reveals that intense geomagnetic disturbances significantly increase the risk of small signal instability. Optimal placement of blocking devices based on sensitivity scenarios results in a significant reduction in the risk index compared to constant and varying induced geoelectric fields scenarios.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2024)
Article
Engineering, Electrical & Electronic
Xuejian Zhang, Wenxin Kong, Nian Yu, Huang Chen, Tianyang Li, Enci Wang
Summary: The intensity estimation of geomagnetically induced currents (GICs) varies depending on the method used. The estimation using field magnetotelluric (MT) data provides the highest accuracy, followed by the estimation using 3D conductivity models and the estimation using a 1D conductivity model. The GICs in the North China 1000-kV power grid have reached a very high-risk level, with C3 and C4 having a significant impact on the geoelectric field and GICs.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2024)
Article
Engineering, Electrical & Electronic
Yue Pan, Shunjiang Lin, Weikun Liang, Xiangyong Feng, Xuan Sheng, Mingbo Liu
Summary: This paper introduces the concept and model of offshore-onshore regional integrated energy system, and proposes a stochastic optimal dispatch model and an improved state-space approximate dynamic programming algorithm to solve the model. The case study demonstrates the effectiveness and high efficiency of the proposed method in improving economic and environmental benefits.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2024)
Article
Engineering, Electrical & Electronic
Mohammad Eydi, Reza Ghazi, Majid Oloomi Buygi
Summary: Proportional current sharing, voltage restoration, and SOCs balancing in DC microgrid control algorithms are the leading challenges. This paper proposes a novel communication-less control method using a capacitor and a DC/DC converter to stabilize the system and restore the DC bus voltage. The method includes injecting an AC signal into the DC bus, setting the current of energy storage units based on frequency and SOC, and incorporating droop control for system stability. Stability analysis and simulation results validate the effectiveness of the proposed method.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2024)
Article
Engineering, Electrical & Electronic
Xiangjian Meng, Xinyu Shi, Weiqi Wang, Yumin Zhang, Feng Gao
Summary: With the increasing penetration of photovoltaic power generation, regional power forecasting becomes critical for stable and economical operation of power systems. This paper proposes a minute-level regional PV power forecasting scheme using selected reference PV plants. The challenges include the lack of complete historical power data and the heavy computation burden. The proposed method incorporates a novel reference PV plant selection method and a flexible approach to decrease the accumulated error of rolling forecasting.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2024)
Article
Engineering, Electrical & Electronic
Huabo Shi, Yuhong Wang, Xinwei Sun, Gang Chen, Lijie Ding, Pengyu Pan, Qi Zeng
Summary: This article investigates the dynamic stability characteristics of the full size converter variable speed pumped storage unit and proposes improvements for the control strategy. The research is important for ensuring the safe and efficient operation of the unit.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2024)
Article
Engineering, Electrical & Electronic
Firmansyah Nur Budiman, Makbul A. M. Ramli, Houssem R. E. H. Bouchekara, Ahmad H. Milyani
Summary: This paper proposes an optimal harmonic power flow framework for the daily scheduling of a grid-connected microgrid, which addresses power quality issues and ensures effective control through demand side management.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2024)
Article
Engineering, Electrical & Electronic
Cong Zeng, Ziyu Chen, Jizhong Zhu, Fellew Ieee
Summary: This paper introduces a distributed solution method for the multi-objective OPF problem, using a coevolutionary multi-objective evolutionary algorithm and the idea of decomposition. The problem is alleviated by decomposing decision variables and objective functions, and a new distributed fitness evaluation method is proposed. The experimental results demonstrate the effectiveness of the method and its excellence in large-scale systems.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2024)
