摘要
The integrated energy system based on ubiquitous power Internet of Things (IoT) has the characteristics of ubiquitous connection of everything, complex energy conversion mode, and unbalanced supply-demand relationship. It brings strong random disturbance to the power grid, which deteriorates the comprehensive control performance of automatic generation control. Therefore, a novel deep reinforcement learning algorithm, namely, collaborative learning actor-critic strategy, is proposed. It is oriented to different exploration horizons, has the advantage on experience sharing mechanism and can continuously coordinate the key behavioral strategies. Simulation tests are performed on the two-area integrated energy system and the four-area integrated energy system based on ubiquitous power IoT. Comparative analyses show that the proposed algorithm can efficiently solve the problem of strong random disturbance, and has better convergence characteristic and generalization performance. Besides, it can realize the optimal cooperative control of multiarea integrated energy system efficiently.
学科与关键词
- Automatic Generation Control for Distributed Multi-Region Interconnected Power System with Function ApproximationLiu, Yuchen; Zhang, Le*; Xi, Lei; Sun, Qiuye; Zhu, JizhongFrontiers in Energy Research, 2021, 9: 700069.被引 4
- Coordinated load frequency control of multi-area integrated energy system using multi-agent deep reinforcement learningLi, Jiawen; Yu, Tao*; Zhang, XiaoshunApplied Energy, 2022, 306: 117900.被引 73
- Deep Reinforcement Learning Based Multi-Objective Integrated Automatic Generation Control for Multiple Continuous Power DisturbancesLi, Jiawen; Yu, Tao*IEEE Access, 2020, 8: 156839-156850.被引 20
