Hybrid process model and smart policy network of electric-vehicle resources for instantaneous power flow imbalances. (15th May 2022)

• Record Type: Journal Article
• Authors: Dong, Chaoyu; Sun, Jianwen; Li, Yanran; Zheng, Yan; Hao, Jianye; Liu, Yang; Jia, Hongjie
• Is Part Of: Applied energy. Volume 314(2022)
• Publication Date: 2022-05-15
• Subjects: Hybrid process model -- Electric vehicles -- Smart policy network -- Adversarial mechanism -- Power flow imbalance -- Process optimization; Power (Mechanics) -- Periodicals; Energy conservation -- Periodicals; Energy conversion -- Periodicals; 621.042
• DOI: 10.1016/j.apenergy.2022.118531
• Languages: English
• ISSNs: 0306-2619

Abstract

Abstract: The technology development of power electronics and battery empowers electric vehicles as practical approaches for the compensation of instantaneous power flow imbalance. To utilize the response capability of distributed vehicles and stabilize the grid frequency caused by instant power mismatch, a process model hybridizing the data-driven and conventional modes is designed for the electrical-grid-electric-vehicle system. Due to the real-time variations of power system, electric vehicles, and renewable energies, the hybrid process model directly interacts with the system feedback to remove the sophisticated model establishment, which effectively establishes the mapping relationship between system states and intelligently processing demands. Based on the hybrid process model, the smart policy network with an adversarial mechanism is then developed to enhance the model behavior. To fulfill the continuous action requirement and speed up the policy convergence, a proximal optimization strategy is further introduced to adjust hyperparameters through a stochastic ratio automatically. Bridging the huge volume of real-time dynamics and the action domain, the sufficient utilization of various operation states is achieved in the proposed process model and policy network, which notably detects the optimal operation point and reduces the power flow imbalance. The developed hybrid process model and smart policy network are validated through an electrical-grid-electric-vehicle system by comprehensive studies from four aspects of the process performance, generalization, robustness, and efficiency. Compared with the linear and naive hybrid process methods, 3.95 times superior integration performance and the improved evolution process of 64.5% improvement are both demonstrated as well as the robustness facing various circumstances. Highlights: A hybrid process model is developed to evolve the vehicle-grid process center. A smart policy network is deployed to handle large-scale data of electric vehicles. An adversarial neural network is introduced to assist the effective policy update. Proximal optimization is employed for the network gradient updating. Effectiveness, generalization, robustness, efficiency are verified facing imbalance.