基于自适应神经动力学算法的电-氢综合能源系统分布式能量管理方法  

Distributed Energy Management Method for Electric-hydrogen Integrated Energy System Based on Adaptive Neurodynamics Algorithm

作　　者：管文博 李基源 常馨月 薛屹洵 苏珈 李泽宁 GUAN Wenbo;LI Jiyuan;CHANG Xinyue;XUE Yixun;SU Jia;LI Zening(College of Electrical and Power Engineering,Taiyuan University of Technology,Taiyuan 030024,China;Key Laboratory of Cleaner Intelligent Control on Coal&Electricity,Ministry of Education,Taiyuan University of Technology,Taiyuan 030024,China;Energy Internet Key Laboratory of Shanxi Province,Taiyuan University of Technology,Taiyuan 030024,China)

机构地区：[1]太原理工大学电气与动力工程学院,山西太原030024 [2]煤电清洁智能控制教育部重点实验室(太原理工大学),山西太原030024 [3]能源互联网山西省重点实验室(太原理工大学),山西太原030024

出　　处：《山东电力技术》2025年第2期13-22,共10页Shandong Electric Power

基　　金：国家自然科学基金项目(52407133);山西省基础研究计划青年项目(202303021212059)。

摘　　要：近年来,在能源需求持续攀升和氢能技术不断发展的背景下,电-氢综合能源系统引起了学界的广泛关注。随着大量分布式资源的接入,系统呈现出愈加显著的多主体特征,给电-氢综合能源系统的能量管理带来了新的挑战。文中提出了一种基于自适应神经动力学算法的电-氢综合能源系统分布式能量管理策略。首先,考虑火力机组、风光机组、电解槽、储氢罐、氢化工等能源设备的运行成本及约束,建立了电-氢综合能源系统能量管理模型。其次,针对此优化模型的求解,建立了一种分布式自适应神经动力学优化算法。该算法不仅保留了神经动力学算法计算时间短、速度快的特点,还减少了自变量初值对求解的影响。在算例中,所提方法同时与集中式方法和交替方向乘子法的求解结果对比,验证了所提方法在计算效率上的优越性和有效性。Recent years,against the background of the continuous rise in energy demand and the continuous development of hydrogen energy technology,the electric-hydrogen integrated energy system has attracted extensive attention in the academic community.With the access of a large number of distributed resources,the system presents more and more significant multi agent characteristics,which brings new challenges to the energy management of electric-hydrogen integrated energy system.In this paper,a distributed energy management strategy for electric-hydrogen integrated energy system based on adaptive neuraldynamics algorithm is proposed.Firstly,considering the operating costs and constraints of thermal units,wind power units,photovoltaic units,electrolysis tanks,hydrogen storage tanks,hydrogen chemicals and other energy equipment,an energy management model for the electric-hydrogen integrated energy system is established.Secondly,a distributed adaptive neuraldynamics optimization algorithm is developed to solve the optimization model.The algorithm not only retains the characteristics of short computation time and speed of the neurodynamic algorithm,but also reduces the influence of the initial value of the independent variables on the solution.In case studies,comparisons of the proposed method with the solution results of the centralized method and the alternating direction multiplier method verifies the superiority of the used method in terms of computational efficiency and effectiveness.

关 键 词：电-氢综合能源系统 分布式能量管理 自适应神经动力学算法 

分 类 号：TM715[电气工程—电力系统及自动化] TK01[动力工程及工程热物理]