基于改进SAC算法的多微电网经济优化调度研究

赵志华; 倪欢

doi:10.19912/j.0254-0096.tynxb.2024-1835

PDF(5895 KB)

太阳能学报 ›› 2026, Vol. 47 ›› Issue (2) : 355-364. DOI: 10.19912/j.0254-0096.tynxb.2024-1835

基于改进SAC算法的多微电网经济优化调度研究

赵志华, 倪欢

作者信息 +

RESEARCH ON MULTI-MICROGRID DAY-AHEAD ECONOMIC OPTIMIZATION SCHEDULING BASED ON IMPROVED SAC ALGORITHM

Zhao Zhihua, Ni Huan

Author information +

文章历史 +

摘要

针对考虑电动汽车和光伏、风电出力的多微电网系统模型,以系统总运行成本最小化为目标函数,建立起基于深度强化学习的多微电网系统经济优化调度框架,并运用改进软演员-评论家（SAC）算法的框架设计状态、动作、奖励函数和神经网络结构,通过对激活函数和经验回放池的改进,提高了算法的搜索能力和防局部最优解的能力,实现了基于改进SAC算法的多微电网经济优化调度。经过仿真对比分析,该算法得到的调度策略降低了总运行成本。

Abstract

Aiming at the multi-microgrid system model considering the output of electric vehicles, photovoltaics and wind power, an economic optimization scheduling structure for multi microgrid systems based on deep reinforcement learning is established with the minimization of the total operating cost of the system as the objective function, and the state, action, reward function and neural network structure of the improved SAC algorithm are designed by using the framework of the improved SAC algorithm. After simulation and comparative analysis, the scheduling strategy obtained by the algorithm reduces the total operating cost.

导出引用

赵志华, 倪欢. 基于改进SAC算法的多微电网经济优化调度研究[J]. 太阳能学报. 2026, 47(2): 355-364 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1835

Zhao Zhihua, Ni Huan. RESEARCH ON MULTI-MICROGRID DAY-AHEAD ECONOMIC OPTIMIZATION SCHEDULING BASED ON IMPROVED SAC ALGORITHM[J]. Acta Energiae Solaris Sinica. 2026, 47(2): 355-364 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1835

中图分类号： TM73

参考文献

[1] 马丽叶, 刘美思, 尹钰, 等. 主动配电网中多微网鲁棒环境经济调度研究[J]. 太阳能学报, 2020, 41(11): 1-10.
MA L Y, LIU M S, YIN Y, et al.Robust environment economic scheduling of multimicrogrids in active distribution network[J]. Acta energiae solaris sinica, 2020, 41(11): 1-10.
[2] 陈友芹, 蒋炯, 殷展翔, 等. 基于NCPSO的微网群优化调度策略研究[J]. 太阳能学报, 2022, 43(8): 477-483.
CHEN Y Q, JIANG J, YIN Z X, et al.Research on optimal scheduling strategy of microgrid clusters based on NCPSO[J]. Acta energiae solaris sinica, 2022, 43(8): 477-483.
[3] 冉金周, 李华强, 李彦君, 等. 考虑灵活性供需匹配的孤岛微网优化调度策略[J]. 太阳能学报, 2022, 43(5): 36-44.
RAN J Z, LI H Q, LI Y J, et al.Optimal scheduling of isolated microgrid considering flexible power supply and demand[J]. Acta energiae solaris sinica, 2022, 43(5): 36-44.
[4] QIAO J F, WANG G M, LI W J, et al.An adaptive deep Q-learning strategy for handwritten digit recognition[J]. Neural networks, 2018, 107: 61-71.
[5] 江昌旭, 刘晨曦, 林铮, 等. 基于深度强化学习的电力系统暂态稳定控制策略研究综述[J]. 高电压技术, 2023, 49(12): 5171-5186.
JIANG C X, LIU C X, LIN Z, et al.Review of power system transient stability control strategies based on deep reinforcement learning[J]. High voltage engineering, 2023, 49(12): 5171-5186.
[6] 李航, 李国杰, 汪可友. 基于深度强化学习的电动汽车实时调度策略[J]. 电力系统自动化, 2020, 44(22): 161-167.
LI H, LI G J, WANG K Y.Real-time dispatch strategy for electric vehicles based on deep reinforcement learning[J]. Automation of electric power systems, 2020, 44(22): 161-167.
[7] KIUMARSI B, LEWIS F L.Actor-critic-based optimal tracking for partially unknown nonlinear discrete-time systems[J]. IEEE transactions on neural networks and learning systems, 2015, 26(1): 140-151.
[8] 葛磊蛟, 范延赫, 来金钢, 等. 面向低碳经济的人工智能赋能微电网优化运行技术[J]. 高电压技术, 2023, 49(6): 2219-2238.
GE L J, FAN Y H, LAI J G, et al.Artificial intelligence enabled microgrid optimization technology for low carbon economy[J]. High voltage engineering, 2023, 49(6): 2219-2238.
[9] 罗建勋, 张玮, 王辉, 等. 基于深度强化学习的微电网优化调度研究[J]. 电力学报, 2023, 38(1): 54-63.
LUO J X, ZHANG W, WANG H, et al.Research on optimal scheduling of micro-grid based on deep reinforcement learning[J]. Journal of electric power, 2023, 38(1): 54-63.
[10] 杨家令, 陈涛, 高赐威. 基于双延迟深度确定性策略梯度算法的微电网能源优化分配策略研究[J]. 电力需求侧管理, 2024, 26(4): 1-8.
YANG J L, CHEN T, GAO C W.Research on energy optimization allocation strategy for microgrids based on double delay deep deterministic strategy gradient algorithm[J]. Power demand side management, 2024, 26(4): 1-8.
[11] MBUWIR B V, RUELENS F, SPIESSENS F, et al.Battery energy management in a microgrid using batch reinforcement learning[J]. Energies, 2017, 10(11): 1846.
[12] 刘林鹏, 朱建全, 陈嘉俊, 等. 基于柔性策略-评价网络的微电网源储协同优化调度策略[J]. 电力自动化设备, 2022, 42(1): 79-85.
LIU L P, ZHU J Q, CHEN J J, et al.Cooperative optimal scheduling strategy of source and storage in microgrid based on soft actor-critic[J]. Electric power automation equipment, 2022, 42(1): 79-85.
[13] 周辉, 张玉, 肖烈禧, 等. 基于改进秃鹰算法的微电网群经济优化调度研究[J]. 太阳能学报, 2024(2): 328-335.
ZHOU H, ZHANG Y, XIAO L X, et al.Research on economic optimal dispatching of microgrid group based on improved vulture algorithm[J]. Acta energiae solaris sinica, 2024(2): 328-335.
[14] 杨丽君, 杨博, 安立明, 等. 考虑电动汽车响应的光储微电网储能优化配置[J]. 太阳能学报, 2020, 41(4): 340-347.
YANG L J, YANG B, AN L M, et al.Optimal configuration of grid-connected PV-and-storage microgrid considering evs’ demand response[J]. Acta energiae solaris sinica, 2020, 41(4): 340-347.
[15] 范静宇. 基于熵的深度强化学习优化算法[D]. 苏州: 苏州大学, 2021.
FAN J Y.Optimization algorithm of deep reinforcement learning based on entropy[D]. Suzhou: Soochow University, 2021.
[16] 张晓莉, 郭仕林, 刘鼎, 等. 基于改进SAC的倒立摆控制算法研究[J]. 电子测量技术, 2024, 47(1): 93-100.
ZHANG X L, GUO S L, LIU D, et al.Research on the control algorithm of inverted pendulum based on improved SAC[J]. Electronic measurement technology, 2024, 47(1): 93-100.
[17] PRIANTO E, KIM M, PARK J H, et al.Path planning for multi-arm manipulators using deep reinforcement learning: soft actor-critic with hindsight experience replay[J]. Sensors, 2020, 20(20): 5911.
[18] 唐超, 张帆. 基于改进SAC算法的机械臂运动规划[J]. 电子科技, 2024, 37(11): 47-54.
TANG C, ZHANG F.Motion planning of manipulator based on improved soft actor-critic algorithm[J]. Electronic science and technology, 2024, 37(11): 47-54.
[19] 罗永建, 刘承锡, 董旭柱. 基于深度强化学习架构的多能互补微网日前经济调度研究[J]. 武汉大学学报(工学版), 2023, 56(11): 1393-1404.
LUO Y J, LIU C X, DONG X Z.Day-ahead economic dispatching of multi-energy complementary micro-grid based on deep reinforcement learning architecture[J]. Engineering Journal of Wuhan University, 2023, 56(11): 1393-1404.
[20] 林振福, 杨铎烔. 基于确定性策略梯度深度强化学习和模仿学习的多源微电网经济优化调度策略[J]. 电工技术, 2023(8): 76-82.
LIN Z F, YANG D T.Economic optimal dispatch strategy for multi-source microgrid based on deep deterministic policy gradient and imitation learning[J]. Electric engineering, 2023(8): 76-82.
[21] WOO J H, WU L, PARK J B, et al.Real-time optimal power flow using twin delayed deep deterministic policy gradient algorithm[J]. IEEE access, 2020, 8: 213611-213618.