基于隐含数据信息挖掘的贝叶斯电采暖负荷预测
|
摘要
冬季电采暖负荷的准确预测对电网安全稳定运行以及电力系统调峰和调频具有重要意义。为充分挖掘冬季电采暖负荷数据中隐含信息,提出基于贝叶斯网络的多变量冬季电采暖负荷预测方法。首先将隐含信息数据中的多变量数据分为可观测数据和隐含数据,依据变量之间的影响机制搭建贝叶斯网络结构,并通过EM(Expectation Maximization Algorithm)算法训练可观测数据信息,获取隐含数据分布,进而基于可观测数据和隐含数据实现冬季电采暖负荷预测。采用北京市电力公司提供的冬季电采暖负荷实测数据进行验证,结果表明,采用贝叶斯网络进行电采暖负荷预测具有较高的预测精度。
The accurate prediction of heating load in winter is of great significance to the safe and stable operation of the power grid and the peaking and frequency regulation of the power system. In order to fully exploit the implicit information in winter heating load data,a multivariable winter heating load forecasting method based on Bayesian network is proposed in this paper. Firstly,the multivariable data in implicit information data is divided into observable data and implicit data.Bayesian network structure is built based on the influence mechanism between variables,and observable data information is trained by EM( expectation maximization algorithm) to obtain hidden data distribution,and then,the heating load forecasting is realized based on observable data and implicit data. The winter heating load is verified through using the measured data in an area provided by Beijing Power Grid Corporation,the results show that the adoption of Bayesian network for heating load forecasting has higher prediction accuracy.
The accurate prediction of heating load in winter is of great significance to the safe and stable operation of the power grid and the peaking and frequency regulation of the power system. In order to fully exploit the implicit information in winter heating load data,a multivariable winter heating load forecasting method based on Bayesian network is proposed in this paper. Firstly,the multivariable data in implicit information data is divided into observable data and implicit data.Bayesian network structure is built based on the influence mechanism between variables,and observable data information is trained by EM( expectation maximization algorithm) to obtain hidden data distribution,and then,the heating load forecasting is realized based on observable data and implicit data. The winter heating load is verified through using the measured data in an area provided by Beijing Power Grid Corporation,the results show that the adoption of Bayesian network for heating load forecasting has higher prediction accuracy.
引文
[1]许汉平,李姚旺,苗世洪,等.考虑可再生能源消纳效益的电力系统“源-荷-储”协调互动优化调度策略[J].电力系统保护与控制,2017,45(17):18-21.Xu Hanping,Li Yaowang,Miao Shihong,et al. Optimization dispatch strategy considering renewable energy consumptive benefits based on“source-load-energy storage”coordination in power system[J]. Power System Protection and Control,2017,45(17):18-21.
[2]林建熙,史俊祎,文福拴,等.计及可控负荷的工业微网源荷协同优化调度[J].电力建设,2018,39(1):1-7.Lin Jianxi,Shi Junyi,Wen Fushuan,et al. Coor-dinated optimal dispatch among generation and loads in industrial microgrids with controllable loads[J]. Electric Power Construction,2018,39(1):1-7.
[3]王黎明,王艳松,魏志远.基于回归分析与神经网络的短期负荷预测[J].电气应用,2007,26(11):37-39.Wang Liming,Wang Yansong,Wei Zhiyuan. Short-term load forecasting algorithm based on regression analysis and the combination of genetic algorithm and neural network[J]. Elec-trotechnical. Application,2007,26(11):37-39.
[4]宋超,黄民翔,叶剑斌.小波分析方法在电力系统短期负荷预测中的应用[J].电力系统及其自动化学报. 2002,14(3):9-11.Song Chao,Huang Minxiang,Ye Jianbin. The application and problems of wavelets used in short-term power load forecasting[J]. Procee-dings of the Csu-epsa,2002,14(3):9-11.
[5]李祥立,王仁瑾,端木琳,等.基于BP神经网络的地板辐射供暖系统逐时负荷预测[J].暖通空调,2011,41(12):95.Li Xiangli,Wang Renjin,Duan Mulin,et al. Hourly heating load prediction of radiant floor heating systems based on BP neural network[J].Heating Ventilating&Air Conditioning,2011,41(12):95.
[6]张经博,郭凌,王朝霞,等.基于遗传算法优化BP神经网络的供暖系统热负荷预测模型[J].四川兵工学报. 2014,35(4):153.Zhang Jingbo,Guo Ling,Wang Zhaoxia,et al. Thermal load forecasting model of heating system based on genetic algorithm optimizat-ion BP neural network[J]. Journal of Ordnance Equipment Engineering,2014,35(4):153.
[7]焦润海,苏辰隽,林碧英,等.基于气象信息因素修正的灰色短期负荷预测模型[J].电网技术,2013,37(3):721-724.Jiao Runhai,Su Chenjun,Lin Biying,et al. Short term load forecasting by grey model with weather factor based correction[J]. Power System Technology,2013,37(3):721-724.
[8]陆宁,武本令,刘颖.基于自适应粒子群优化的SVM模型在负荷预测中的应用[J].电力系统保护与控制,2011,39(15):44-47.LuNing,Wu Benling,Liu Ying. Application of support vector machine model in load forecasting based on adaptive particle swarm optimization[J]. Power System Protection and Control,2011,39(15):44-47.
[9] Douglas A P,Breipohl A M,Lee F N,et al. The impacts of temperature forecast uncertainty on Bayesian load forecasting[J].Power Systems,IEEE Transactions on,1998,13(4):1507-1513.
[10]Lauret P,Fock E,Randrianarivony R,et al. Bayesian neural network approach to short time load forecasting[J]. Energy Conversion and Management,2008,49(5):1156-1166.
[11]Saini L M. Peak load forecasting using Bayesian regularization,Resilient and adaptive backpropagation learning based artificial neural networks[J]. Electric Power Systems Research,2008,78(7):1302-1310.
[12]Cottet R,Smith M. Bayesian modeling and forecasting of intraday electricity load[J]. Journal of the American Statistical Association,2003,98(464):839-849.
[13]康重庆,夏清,刘梅.电力系统负荷预测[M].北京:中国电力出版社.
[14]董玉军,黄东,袁秀玲.空气源热泵冷热水机组的系统仿真与实验研究[J].制冷与空调(北京),2006,6(5):52-57.Dong Yujun,Huang Dong,Yuan Xiuling. Numerical simulation and experimental invest-igation on air source heat pump chiller[J]. Refrigeration and Air-conditioning,2006,6(5):52-57.
[15]饶荣水.制冷剂R32特性及其用于空气源热泵热水器的理论循环分析[J].制冷与空调(北京),2010,10(3):79-84.Rao Rongshui. Properties of R32 and its theoretical cycle analysis of air source heat pump water heater[J]. Refrigeration and Air-conditioning,2010,10(3):79-84.
[16]柴沁虎,马国远.空气源热泵低温适应性研究的现状及进展[J].能源工程,2002,9(5):25-31.Chai Qinhu,Ma Guoyuan. State of knowledge and current challenges in the ASHP developed for the cold areas[J]. Energy Engineering,2002,9(5):25-31.
[17]康守亚,李嘉龙,李燕珊,等.考虑峰谷分时电价策略的源荷协调多目标发电调度模型[J].电力系统保护与控制,2016,44(11):83-89.Kang Shouya,Li Jialong,Li Yanshan,et al. Multi-objective generation scheduling model of source and load considering the strategy of TOU price[J]. Power System Protection and Control,2016,44(11):83-89.
[18]张颖,容展鹏,张宇雄,等.基于微电网的电网需求响应研究[J].电力系统保护与控制,2015,43(21):20-26.Zhang Ying,Rong Zhanpeng,Zhang Yuxiong,et al. Study of grid demand response based on micro grid[J]. Power System Protection and Control,2015,43(21):20-26.
[19]Roverato A,Studeny M. A Graphical Representation of Equivalence Classes of AMP Chain Graphs[J]. Journal of Machine Learning Research,2006,7:1045-1078.
[20]Koivisto M,Sood K. Exact Bayesian structure discovery in Bayesian networks[J]. Journal of Machine Learning Research,2004,5:5 49-573.
[2]林建熙,史俊祎,文福拴,等.计及可控负荷的工业微网源荷协同优化调度[J].电力建设,2018,39(1):1-7.Lin Jianxi,Shi Junyi,Wen Fushuan,et al. Coor-dinated optimal dispatch among generation and loads in industrial microgrids with controllable loads[J]. Electric Power Construction,2018,39(1):1-7.
[3]王黎明,王艳松,魏志远.基于回归分析与神经网络的短期负荷预测[J].电气应用,2007,26(11):37-39.Wang Liming,Wang Yansong,Wei Zhiyuan. Short-term load forecasting algorithm based on regression analysis and the combination of genetic algorithm and neural network[J]. Elec-trotechnical. Application,2007,26(11):37-39.
[4]宋超,黄民翔,叶剑斌.小波分析方法在电力系统短期负荷预测中的应用[J].电力系统及其自动化学报. 2002,14(3):9-11.Song Chao,Huang Minxiang,Ye Jianbin. The application and problems of wavelets used in short-term power load forecasting[J]. Procee-dings of the Csu-epsa,2002,14(3):9-11.
[5]李祥立,王仁瑾,端木琳,等.基于BP神经网络的地板辐射供暖系统逐时负荷预测[J].暖通空调,2011,41(12):95.Li Xiangli,Wang Renjin,Duan Mulin,et al. Hourly heating load prediction of radiant floor heating systems based on BP neural network[J].Heating Ventilating&Air Conditioning,2011,41(12):95.
[6]张经博,郭凌,王朝霞,等.基于遗传算法优化BP神经网络的供暖系统热负荷预测模型[J].四川兵工学报. 2014,35(4):153.Zhang Jingbo,Guo Ling,Wang Zhaoxia,et al. Thermal load forecasting model of heating system based on genetic algorithm optimizat-ion BP neural network[J]. Journal of Ordnance Equipment Engineering,2014,35(4):153.
[7]焦润海,苏辰隽,林碧英,等.基于气象信息因素修正的灰色短期负荷预测模型[J].电网技术,2013,37(3):721-724.Jiao Runhai,Su Chenjun,Lin Biying,et al. Short term load forecasting by grey model with weather factor based correction[J]. Power System Technology,2013,37(3):721-724.
[8]陆宁,武本令,刘颖.基于自适应粒子群优化的SVM模型在负荷预测中的应用[J].电力系统保护与控制,2011,39(15):44-47.LuNing,Wu Benling,Liu Ying. Application of support vector machine model in load forecasting based on adaptive particle swarm optimization[J]. Power System Protection and Control,2011,39(15):44-47.
[9] Douglas A P,Breipohl A M,Lee F N,et al. The impacts of temperature forecast uncertainty on Bayesian load forecasting[J].Power Systems,IEEE Transactions on,1998,13(4):1507-1513.
[10]Lauret P,Fock E,Randrianarivony R,et al. Bayesian neural network approach to short time load forecasting[J]. Energy Conversion and Management,2008,49(5):1156-1166.
[11]Saini L M. Peak load forecasting using Bayesian regularization,Resilient and adaptive backpropagation learning based artificial neural networks[J]. Electric Power Systems Research,2008,78(7):1302-1310.
[12]Cottet R,Smith M. Bayesian modeling and forecasting of intraday electricity load[J]. Journal of the American Statistical Association,2003,98(464):839-849.
[13]康重庆,夏清,刘梅.电力系统负荷预测[M].北京:中国电力出版社.
[14]董玉军,黄东,袁秀玲.空气源热泵冷热水机组的系统仿真与实验研究[J].制冷与空调(北京),2006,6(5):52-57.Dong Yujun,Huang Dong,Yuan Xiuling. Numerical simulation and experimental invest-igation on air source heat pump chiller[J]. Refrigeration and Air-conditioning,2006,6(5):52-57.
[15]饶荣水.制冷剂R32特性及其用于空气源热泵热水器的理论循环分析[J].制冷与空调(北京),2010,10(3):79-84.Rao Rongshui. Properties of R32 and its theoretical cycle analysis of air source heat pump water heater[J]. Refrigeration and Air-conditioning,2010,10(3):79-84.
[16]柴沁虎,马国远.空气源热泵低温适应性研究的现状及进展[J].能源工程,2002,9(5):25-31.Chai Qinhu,Ma Guoyuan. State of knowledge and current challenges in the ASHP developed for the cold areas[J]. Energy Engineering,2002,9(5):25-31.
[17]康守亚,李嘉龙,李燕珊,等.考虑峰谷分时电价策略的源荷协调多目标发电调度模型[J].电力系统保护与控制,2016,44(11):83-89.Kang Shouya,Li Jialong,Li Yanshan,et al. Multi-objective generation scheduling model of source and load considering the strategy of TOU price[J]. Power System Protection and Control,2016,44(11):83-89.
[18]张颖,容展鹏,张宇雄,等.基于微电网的电网需求响应研究[J].电力系统保护与控制,2015,43(21):20-26.Zhang Ying,Rong Zhanpeng,Zhang Yuxiong,et al. Study of grid demand response based on micro grid[J]. Power System Protection and Control,2015,43(21):20-26.
[19]Roverato A,Studeny M. A Graphical Representation of Equivalence Classes of AMP Chain Graphs[J]. Journal of Machine Learning Research,2006,7:1045-1078.
[20]Koivisto M,Sood K. Exact Bayesian structure discovery in Bayesian networks[J]. Journal of Machine Learning Research,2004,5:5 49-573.