基于改进SAC算法的微网群双层协同优化调度方法

doi:10.16088/j.issn.1001-6600.2025051405

摘要/Abstract

摘要： 针对微网群的传统调度方法存在灵活性不足、计算复杂度高等问题,本文提出一种基于改进SAC算法的微网群传统调度方法。首先,构建一个以最小化运行成本为目标的微网群双层协同优化调度模型,其中上层负责微网群的全局功率优化调度,下层负责各子微网的局部功率优化调度。其次,在传统SAC算法中引入变分自编码器(variational autoencoder,VAE)模型对其进行改进,利用VAE的特征提取能力对高维状态进行降维与关键特征提取,从而降低算法的计算复杂度。然后,在优先经验回放机制的基础上引入时间衰减因子,提高对后进入经验的采用频率,进一步提高算法的学习效率。最后,利用改进的SAC算法和交替方向乘子法分别对上下层模型进行优化求解,通过上下层交互机制,实现微网群的高效协同调度与经济运行。仿真结果表明,相比于基于成本-收益均衡、基于低碳经济导向和基于多利益主体的优化调度方法,本文所提方法的运行成本分别减少14.0%、10.2%和6.4%;负荷平衡率分别提高9.3、6.4和3.6个百分点;能源利用率分别提高10.8、7.6和2.9个百分点。这一结果验证了所提方法在微网群优化调度中的优越性;同时,该方法在应对风光发电预测误差时,也表现出较好的鲁棒性。

关键词: 智能电网, 微网群, 优化调度, SAC算法, 交替方向乘子算法, 变分自编码器

Abstract: Microgrid clusters can enhance the utilization rate of renewable energy and system reliability, but their traditional dispatching methods have problems such as insufficient flexibility and high computational complexity. To address this issue, this paper proposes a two-layer collaborative optimization dispatching method for microgrid clusters based on an improved SAC algorithm. Firstly, a two-layer collaborative optimization dispatching model for microgrid clusters is constructed, aiming to minimize the operation cost, where the upper layer is responsible for the global power optimization dispatching of the microgrid cluster, and the lower layer is responsible for the local power optimization dispatching of each sub-microgrid. Secondly, an improved SAC algorithm is proposed, which introduces a variational autoencoder (VAE) model into the traditional SAC algorithm to utilize the feature extraction ability of VAE to reduce the dimension of high-dimensional states and extract key features, thereby reducing the computational complexity of the algorithm. Then, a time decay factor is introduced on the basis of the prioritized experience replay mechanism to increase the adoption frequency of later-entered experiences, further improving the learning efficiency of the algorithm. Finally, the improved SAC algorithm and the alternating direction method of multipliers are used to optimize and solve the upper and lower layer models of the microgrid cluster respectively. Through the interaction mechanism of the upper and lower layers, efficient collaborative dispatching and economic operation of the microgrid cluster are achieved. Simulation results show that the proposed method outperforms Scheme 1, Scheme 2 and Scheme 3 in terms of total operation cost, load balance rate and energy utilization rate. To be exactly, the operating costs of the proposed method in this paper are reduced by14.0%, 10.2% and 6.4%, respectively; the load balance rate is increased by 9.3 percentage points, 6.4 percentage points and 3.6 percentage points, respectively; and the energy utilization rate is raised by 10.8 percentage points, 7.6 percentage points and 2.9 percentage points respectively. This result verifies the superiority of the proposed method in the optimal dispatch of microgrid clusters. Meanwhile, this method also shows good robustness in dealing with the prediction errors of wind and solar power generations.

Key words: intelligent grid, microgrid clusters, optimal scheduling, soft actor critic, alternating direction method of multipliers, variational autoencoder

中图分类号: TM73;TP18

吕辉, 苏静, 熊枫, 张端宇, 常文涵, 王灿, 马辉. 基于改进SAC算法的微网群双层协同优化调度方法[J]. 广西师范大学学报（自然科学版）, 2026, 44(5): 1-15.

Lü Hui, Su Jing, Xiong Feng, Zhang Duanyu, Chang Wenhan, Wang Can, Ma Hui. Bi-level coordinated optimization scheduling method for microgrid clusters based on improved SAC algorithm[J]. Journal of Guangxi Normal University(Natural Science Edition), 2026, 44(5): 1-15.

参考文献

[1] 杨安全, 代红, 赵清松, 等. 计及源荷不确定性的智能小区能源系统两阶段鲁棒优化调度[J]. 广西师范大学学报(自然科学版), 2024, 42(3): 70-85. DOI: 10.16088/j.issn.1001-6600.2023051804.
[2] 王灿, 张羽, 田福银, 等. 基于双向主从博弈的储能电站与综合能源系统经济运行策略[J]. 电工技术学报, 2023, 38(13): 3436-3446, 3472. DOI: 10.19595/j.cnki.1000-6753.tces.221164.
[3] 李方皓, 刘立群, 吴青峰. 基于嗅探策略黏菌算法的微电网故障定位[J]. 广西师范大学学报(自然科学版), 2025, 43(2): 30-41. DOI: 10.16088/j.issn.1001-6600.2024041301.
[4] 王灿, 张雪菲, 凌凯, 等. 基于区间概率不确定集的微电网两阶段自适应鲁棒优化调度[J]. 中国电机工程学报, 2024, 44(5): 1750-1763. DOI: 10.13334/j.0258-8013.pcsee.221968.
[5] 陶长河, 鲁玲, 张羽, 等. 基于禀赋效应的微电网经济优化运行策略[J]. 电力建设, 2025, 46(7): 82-94.DOI: 10.12204/j.issn.1000-7229.2025.07.007.
[6] 黄堃, 付明, 翟家祥, 等. 基于改进线性化ADMM的多微网经济运行分布式协调优化[J]. 中国电力, 2025, 58(2): 193-202.
[7] 骆国铭, 黄小耘, 范心明. 考虑可再生能源特性的实时电力调度优化研究[J]. 电力科学与技术学报, 2025, 40(3): 163-173. DOI: 10.19781/j.issn.1673-9140.2025.03.018.
[8] 徐意婷, 艾芊. 基于全景理论的多微网聚合优化运行[J]. 电力系统保护与控制, 2015, 43(16): 50-56.
[9] 易宇琴, 许加柱, 张伟明, 等. 考虑两阶段鲁棒优化配置的多微网合作博弈[J]. 电力系统自动化, 2023, 47(22): 149-156. DOI: 10.7500/AEPS20230410002.
[10] 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. DOI: 10.19912/j.0254-0096.tynxb.2020-1287.
[11] 曾智基, 杨苹, 陈燿圣, 等. 基于目标级联法的微网群多主体分布式优化调度[J]. 华北电力大学学报(自然科学版), 2019, 46(2): 25-33. DOI: 10.3969/j.ISSN.1007-2691.2019.02.04.
[12] 金涛, 朱莉, 陈博文, 等. 基于合作博弈的微电网群运行优化方法研究[J]. 智慧电力, 2022, 50(3): 15-21, 29. DOI: 10.3969/j.issn.1673-7598.2022.03.004.
[13] 吴成辉, 林声宏, 夏成军, 等. 基于模型预测控制的微电网群分布式优化调度[J]. 电网技术, 2020, 44(2): 530-538. DOI: 10.13335/j.1000-3673.pst.2019.0772.
[14] 刘俊峰, 陈剑龙, 王晓生, 等. 基于深度强化学习的微能源网能量管理与优化策略研究[J]. 电网技术, 2020, 44(10): 3794-3803. DOI: 10.13335/j.1000-3673.pst.2020.0144.
[15] 赵鹏杰, 吴俊勇, 王燚, 等. 基于深度强化学习的微电网优化运行策略[J]. 电力自动化设备, 2022, 42(11): 9-16. DOI: 10.16081/j.epae.202205032.
[16] 毛亚哲, 何柏娜, 王德顺, 等. 基于改进深度强化学习的智能微电网群控制优化方法[J]. 智慧电力, 2021, 49(3): 19-25, 58. DOI: 10.3969/j.issn.1673-7598.2021.03.004.
[17] 王鲁浩, 张淑芳, 张凯, 等. 计及P2P电力交易不确定性的微网群区间联盟形成博弈[J]. 电力系统保护与控制, 2025, 53(18): 109-119. DOI: 10.19783/j.cnki.pspc.241465.
[18] 周雪松, 张宇轩, 马幼捷, 等. 融入SAC算法的光储微网混合储能自驱优级联自抗扰控制[J]. 电力系统保护与控制, 2025, 53(13): 93-104. DOI: 10.19783/j.cnki.pspc.241244.
[19] Wang C, Wang M C, Wang A Q, et al. Multiagent deep reinforcement learning-based cooperative optimal operation with strong scalability for residential microgrid clusters[J]. Energy, 2025, 314: 134165.
[20] Yan K, Su J Y, Huang J, et al. Chiller fault diagnosis based on VAE-enabled generative adversarial networks[J]. IEEE Transactions on Automation Science and Engineering, 2022, 19(1): 387-395. DOI: 10.1109/TASE.2020.3035620.
[21] 檀勤良, 曾贾斌, 吕函谕, 等. 考虑源网荷储协同的配网侧分布式光伏市场交易策略优化[J]. 中国电力, 2025, 58(10): 39-49. DOI: 10.11930/j.issn.1004-9649.202503052.
[22] Mhanna S, Verbič G, Chapman A C. Adaptive ADMM for distributed AC optimal power flow[J]. IEEE Transactions on Power Systems, 2019, 34(3): 2025-2035. DOI: 10.1109/TPWRS.2018.2886344.
[23] 赵紫嫣, 崔双喜, 樊小朝, 等. 考虑经济环保效益的微网群多目标协调优化[J]. 可再生能源, 2019, 37(3): 372-378. DOI: 10.13941/j.cnki.21-1469/tk.2019.03.010.
[24] 谢准, 陆菀珺, 李大鹏, 等. 基于价格机制的微网群三层主体交易策略[J]. 太阳能学报, 2024, 45(5): 391-399. DOI: 10.19912/j.0254-0096.tynxb.2022-1988.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed