严干贵;阚天洋;杨玉龙;张薇;

• 1:现代电力系统仿真控制与绿色电能新技术教育部重点实验室(东北电力大学)

摘要(Abstract)：

分布式电采暖具备可时移特性,能够作为需求响应资源,但其数量多、单体容量小,调度中心难以直接控制,且传统优化方法难以满足调度时效性。应用深度学习实现了无需热力学模型分析户用电采暖单元温变–功率动态关系,构建了包含负荷聚集商和楼宇级控制的调度架构。提出改进的深度确定性策略梯度(deepdeterministicpolicygradient,DDPG)算法作为楼宇级控制策略,构建了改进算法的框架及网络结构,网络训练收敛后可用于在线决策控制。日前调度场景下改进算法在线应用耗时仅耗时0.35s,且在多维度输入场景收敛能力更优。深度学习描述电采暖单元温变–功率关系的有效性通过仿真实验进行了证实。仿真结果表明所提架构相比现行模式更易通过实时电价动态增加/降低引导电采暖负荷减少/增多,提高了电采暖负荷侧需求响应能力;同时使等效负荷标准差由65.6kW降低到37.3kW,减小聚合负荷峰谷差;在保障用户热舒适前提下,用户费用由1031.4元降低到936.1元,减少了用户成本,实现了调度户用电采暖参与需求响应的有效性和经济性。

关键词(KeyWords)： 电采暖;需求响应;深度强化学习;优化调度;DDPG算法;人工智能

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(51907020)~~

作者(Author): 严干贵;阚天洋;杨玉龙;张薇;

Email:

DOI: 10.13335/j.1000-3673.pst.2020.0252a

参考文献(References)：

• [1]孙婧卓,江全元,程中林,等．大规模电储热参与调峰辅助双边交易容量及价格区间优化模型[J]．电网技术,2019,43(6):1995-2001.Sun Jingzhuo,Jiang Quanyuan,Cheng Zhonglin,et al.Capacity and price range optimization model for large-scale electric heat storage participating in auxiliary peaking service in bilateral transactions[J].Power System Technology,2019,43(6):1995-2001(in Chinese)．
• [2]中能智库．电网侧储能僵局：国家电网踩下“急刹车”未来将何去何从[EB/OL]．北京：搜狐新闻[2019-12-30].http://www.sohu.com/a/333008801_777609,2019-08-11．
• [3]黄亚峰,朱玉杰,穆钢,等．基于温度预报的户用电采暖负荷可调节能力评估[J]．电网技术,2018,42(8):2487-2493.Huang Yafeng,Zhu Yujie,Mu Gang,et al.Evaluation of adjustable capacity of household electrical heating load based on temperature forecast[J].Power System Technology,2018,42(8):2487-2493(in Chinese)．
• [4]严干贵,杨玉龙．电力辅助服务市场下电采暖促进风电消纳的经济性分析[J]．全球能源互联网,2019,2(3):309-316.Yan Gangui,Yang Yulong.Economic analysis of electric heating for wind power consumption under the background of ancillary service market[J].Journal of Global Energy Interconnection,2019,2(3):309-316(in Chinese)．
• [5]Papaefthymiou G,Hasche B,Nabe C.Potential of heat pumps for demand side management and wind power integration in the German electricity market[J].IEEE Transactions on Sustainable Energy,2012,3(4):636-642．
• [6]李鹏,杨玉龙,黄越辉,等．综合热电负荷控制下的省级电网风电并网研究[J]．西安交通大学学报,2014,48(2):69-73.Li Peng,Yang Yulong,Huang Yuehui,et al.Wind power integration in provincial power grid under electricity and heating load control[J].Journal of Xi'an Jiaotong University,2014,48(2):69-73(in Chinese)．
• [7]李亚平,姚建国,雍太有,等．居民温控负荷聚合功率及响应潜力评估方法研究[J]．中国电机工程学报,2017,37(19):5519-5528.Li Yaping,Yao Jianguo,Yong Taiyou,et al.Estimation approach to aggregated power and response potential of residential thermostatically controlled loads[J].Proceedings of the CSEE,2017,37(19):5519-5528(in Chinese)．
• [8]孙毅,刘昌利,刘迪,等．面向居民用户群的多时间尺度需求响应协同策略[J]．电网技术,2019,43(11):4170-4177.Sun Yi,Liu Changli,Liu Di,et al.A multi-time scale demand response collaborative strategy for residential user groups[J].Power System Technology,2019,43(11):4170-4177(in Chinese)．
• [9]孙毅,杨艳敏,许鹏,等．基于云模型的用户群负荷调控算法[J]．电网技术,2017,41(8):2611-2617.Sun Yi,Yang Yanmin,Xu Peng,et al.A user group load control algorithm based on cloud model[J].Power System Technology,2017,41(8):2611-2617(in Chinese)．
• [10]马汉杰,林霞,胥晓晖,等．基于自适应粒子群算法的智能家居管理系统负荷优化模型[J]．山东大学学报：工学版,2017,47(6):57-62.Ma Hanjie,Lin Xia,Xu Xiaohui,et al.Load optimization model of smart home management system based on adaptive particle swarm optimization[J].Journal of Shandong University:Engineering Science Edition,2017,47(6):57-62(in Chinese)．
• [11]杨斌,陈振宇,阮文骏,等．基于多种群协同进化遗传算法的智能小区需求响应调度策略[J]．电力需求侧管理,2019,21(2):10-14.Yang Bin,Chen Zhenyu,Ruan Wenjun,et al.Demand response dispatching strategy for intelligent community based on multi-group co-evolution gen[J].Power Demand Side Management,2019,21(2):10-14(in Chinese)．
• [12]Naji S,Keivani A,Shamshirband S,et al.Estimating building energy consumption using extreme learning machine method[J].Energy,2016(97):506-516．
• [13]胡伟,郑乐,闵勇,等．基于深度学习的电力系统故障后暂态稳定评估研究[J]．电网技术,2017,41(10):3140-3146.Hu Wei,Zheng Le,Min Yong,et al.Research on power system transient stability assessment based on deep learning of big data technique[J].Power System Technology,2017,41(10):3140-3146(in Chinese)．
• [14]陈振宇,刘金波,李晨,等．基于LSTM与XGBoost组合模型的超短期电力负荷预测[J]．电网技术,2020,44(2):614-620.Chen Zhenyu,Liu Jinbo,Li Chen,et al.Ultra short-term power load forecasting based on combined LSTM-XGBoost model[J].Power System Technology,2020,44(2):614-620(in Chinese)．
• [15]范士雄,李立新,王松岩,等．人工智能技术在电网调控中的应用研究[J]．电网技术,2020,44(2):401-411.Fan Shixiong,Li Lixin,Wang Songyan,et al.Application analysis and exploration of artificial intelligence technology in power grid dispatch and control[J].Power System Technology,2020,44(2):401-411(in Chinese)．
• [16]李明节,陶洪铸,许洪强,等．电网调控领域人工智能技术框架与应用展望[J]．电网技术,2020,44(2):393-400.Li Mingjie,Tao Hongtao,Xu Hongqiang,et al.The technical framework and application prospect of artificial intelligence application in the field of power grid dispatching and control[J].Power System Technology,2020,44(2):393-400(in Chinese)．
• [17]孙毅,刘迪,李彬,等．深度强化学习在需求响应中的应用[J]．电力系统自动化,2019,43(5):183-194.Sun Yi,Liu Di,Li Bin,et al.Application of deep reinforcement learning in demand response[J].Automation of Electric Power Systems,2019,43(5):183-194(in Chinese)．
• [18]张自东,邱才明,张东霞,等．基于深度强化学习的微电网复合储能协调控制方法[J]．电网技术,2019,43(6):1914-1921.Zhang Zidong,Qiu Caiming,Zhang Dongxia,et al.A coordinated control method for hybrid energy storage system in microgrid based on deep reinforcement learning[J].Power System Technology,2019,43(6):1914-1921(in Chinese)．
• [19]Yang G,Zhang F,Gong C,et al.Application of a deep deterministic policy gradient algorithm for energy-aimed timetable rescheduling problem[J].Energies,2019,12(18):3461．
• [20]Shi D,Li X,Li M,et al.Optimal transportation network company vehicle dispatching via deep deterministic policy gradient[C]//International Conference on Wireless Algorithms,Systems,and Applications.Springer,Cham,2019:297-309．
• [21]刘红敏,王一初,龚志豪,等．基于神经网络的船舶舱室热舒适度研究[J]．上海海事大学学报,2020,41(1):100-106.Liu Hongmin,Wang Yichu,Gong Zhihao,et al.Research on thermal comfort of ship cabins based on neural network[J].Journal of Shanghai Maritime University,2020,41(1):100-106(in Chinese)．
• [22]Zhang Sheng,Lin Zhang.Standard effective temperature based adaptive-rational thermal comfort model[J].Applied Energy,2020,264．
• [23]张慧．深度学习中优化算法的研究与改进[D]．北京：北京邮电大学,2018.