基于PSO-LSSVM的海水淡化负荷预测
|
摘要
为了将海水淡化负荷与分布式可再生能源或电网结合协同运行,进一步提高海水淡化用户的综合经济效益,提出了精准预测海水淡化负荷的方法。首先对影响海水淡化负荷的相关因素应用灰色关联分析理论构建相似日的小样本集合,而后建立多输入单输出的最小二乘支持向量机(LSSVM)模型。针对LSSVM模型,提出了通过粒子群算法(PSO)优化相关参数γ和σ~2的新预测方法。最后利用某海岛冬季用水数据对模型进行仿真验证,结果表明,该模型可达到参数最优化选择的目的,提高了预测精度,能够满足海水淡化负荷预测的需要。
In order to further improve the comprehensive economic benefits of seawater desalination users through the coordinated operation of seawater desalination load, distributed renewable energy and power grid, this paper proposes a method to accurately predict the seawater desalination load. Firstly, a small sample set of similar day is established for related factors affecting the seawater desalination load with gray correlation analysis theory. Then a multi-input single-output least squares support vector machine(LSSVM)model is established. In the light of the LSSVM model, a new prediction method for optimizing related parameters γ and σ~2 by particle swarm optimization(PSO) is proposed. Finally, the model is validated by using the water consumption data from an island in winter. The results show that the model can achieve the purpose of parameter optimization, improve the prediction accuracy and meet the needs of the seawater desalination load forecasting.
In order to further improve the comprehensive economic benefits of seawater desalination users through the coordinated operation of seawater desalination load, distributed renewable energy and power grid, this paper proposes a method to accurately predict the seawater desalination load. Firstly, a small sample set of similar day is established for related factors affecting the seawater desalination load with gray correlation analysis theory. Then a multi-input single-output least squares support vector machine(LSSVM)model is established. In the light of the LSSVM model, a new prediction method for optimizing related parameters γ and σ~2 by particle swarm optimization(PSO) is proposed. Finally, the model is validated by using the water consumption data from an island in winter. The results show that the model can achieve the purpose of parameter optimization, improve the prediction accuracy and meet the needs of the seawater desalination load forecasting.
引文
[1]满曰南,王晓娟,王银涛,等.海水淡化技术研究新进展和发展趋势[J].工业水处理,2014,34(11):8-12.MAN Yuenan, WANG Xiaojuan, WANG Yintao, et al.New progress and development trend of seawater desalination technology[J]. Industrial Water Treatment,2014, 34(11):8-12.
[2]张建华,于雷,刘念,肖锐.含风/光/柴/蓄及海水淡化负荷的微电网容量优化配置[J].电工技术学报,2014,29(02):102-112.ZHANG Jianhua, YU Lei, LIU Nian, XIAO Rui.Optimized configuration of microgrid capacity with wind/light/firewood/storage and seawater desalination load[J].Journal of Electrotechnics, 2014, 29(02):102-112.
[3]段帅.含风/光/柴/蓄及海水淡化负荷的微电网优化调度方法[D].华北电力大学,2014.
[4] CHEN Y,LUH P B,GUAN C,et al. Short-term load forecasting:similar day-based wavelet neural networks[J].IEEE Transactions on Power Systems,2010, 25(1):322-330.
[5] CUI M J, KE D P, SUN Y Z, et al. Wind power ramp events forecasting using a stochastic scenario generation method[J]. IEEE Transactions on Sustainable Energy,2015, 6(2):422-433.
[6]林顺福,郝朝,汤晓栋等.基于数据挖掘的楼宇短期负荷预测方法研究[J].电力系统保护与控制,2016,44(7):83-89.LIN Shunfu,HAO Zhao,TANG Xiaodong,et al. Research on short-term load forecasting method of buildings basedon data mining[J]. Power System Protection and Control,2016,44(7):83-89.
[7]杨尚宝.我国海水淡化产业发展述评2016[J].水处理技术,2017,43(10):1-3+6.YANG Shangbao. Review on the development of seawater desalination industry in China 2016[J]. Water Treatment Technology,2017,43(10):1-3+6.
[8] UNIVERSITY Y. The future of seawater desalination:energy, technology, and the environment.[J]. Science,2011, 333(6043):712-717.
[9]丁晓,孙虹,郑海雁,季聪,徐金玲,仲春林,熊政.基于配用电大数据的短期负荷预测[J].电力工程技术,2018,37(3):21-27.DING Xiao, SUN Hong, JI Cong, et al. Short-term load forecasting based on allocation of electricity big data[J].Power engineering technology, 2018,37(3):21-27.
[10] YU H, CHEN Y, HASSAN S G,et al. Prediction of the temperature in a Chinese solar greenhouse based on LSSVM optimized by improved PSO[J]. Computers&Electronics in Agriculture, 2016, 122:94-102.
[11] AHMADI, ALI M. Toward reliable model for prediction drilling fluid density at wellbore conditions:A LSSVM model[J]. Neurocomputing, 2016, 211:143-149.
[12] CAO H Q, XU J, KE D P, et al. Economic dispatch of micro-grid based on improved particle-swarm optimization algorithm[C]. North American Power Symposium(NAPS), Denver, CO, USA, Sep. 18-20,2016.
[13]梁承红,姜宏,邢红宏.反渗透海水淡化技术的发展与应用[J].海军航空工程学院学报,2007, 22(4):494-496.LIANG Chenhong, JIANG Hong, XING Honghong.Development and application of reverse osmosis seawater desalination technology[J]. Journal of Naval Aeronautical Engineering Institute, 2007, 22(4):494-496.
[14]叶晓琰,佘旭南,胡敬宁,等.年产万吨级海水淡化高压泵关键技术研究与工程应用[J].水处理技术,2015(10):95-99.YE Xiaoyan, YU Xunan, HU Jingyu, et al. Key technology research and engineering application of annual production of 10, 000-ton seawater desalination high pressure pump[J]. Water Treatment Technology, 2015(10):95-99.
[15]刘文霞,徐晓波,周樨.基于支持向量机的纯电动公交车充/换电站日负荷预测[J].电力自动化设备,2014, 34(11):41-47.LIU Wenxia,XU Xiaobo,ZHOU Xi. Daily load forecasting of pure electric bus charging/changing station based on support vector machine[J]. Power Automation Equipment,2014, 34(11):41-47.
[16]张平,潘学萍,薛文超.基于小波分解模糊灰色聚类和BP神经网络的短期负荷预测[J].电力自动化设备,2012, 32(11):121-125.ZHANG Ping, PAN Xueping,XUE Wenchao. Short-term load forecasting based on wavelet decomposition and fuzzy grey clustering and BP neural network[J]. Power Automation Equipment, 2012, 32(11):121-125.
[17]李鑫滨,张娟,张岩,等.基于D-S证据理论的相似日支持向量机短期负荷预测[J].电网技术,2010(7):143-147.LI Xinbin, ZHANG Juan, ZHANG Yan, et al. Short-term load forecasting of similar daily support vector machines based on D-S evidence theory[J]. Power Grid Technology,2010(7):143-147.
[18]莫维仁,张伯明,孙宏斌,等.短期负荷预测中选择相似日的探讨[J].清华大学学报(自然科学版),2004, 44(1):106-109.MO Weiren, ZHANG Boming, SUN Hongbin, et al.Discussion on selecting similar days in short-term load forecasting[J]. Journal of Tsinghua University(Natural Science Edition), 2004, 44(1):106-109.
[19]刘梦良,刘晓华,高荣.基于相似日小波支持向量机的短期电力负荷预测[J].电工技术学报,2006, 21(11):59-64.LIU Mengliang, LIU Xiaohua, GAO Rong. Short-term load forecasting based on similar daily wavelet support vector machine[J]. Journal of Electrotechnics, 2006, 21(11):59-64.
[20]汲国强,汪鸿,王梦,陈建华,单体华,宋宗耘.基于大用户行为属性挖掘和LS-SVM的钢铁行业用电量预测研究[J].智慧电力,2018,46(9):60-65.JI Guoqiang, WANG Hong, WANG Meng, et al. Research on electricity consumption forecast of steel industry based on large user behavior attribute mining and LS-SVM[J].Smart Power,2018,46(9):60-65.
[21] SHEN X, CHEN F, HE T, et al. A new dynamical particle swarm optimization based on principle free entropy minimization[C].Tianjin:Fifth International Conference on Natural Computation, 2009,14-16.
[2]张建华,于雷,刘念,肖锐.含风/光/柴/蓄及海水淡化负荷的微电网容量优化配置[J].电工技术学报,2014,29(02):102-112.ZHANG Jianhua, YU Lei, LIU Nian, XIAO Rui.Optimized configuration of microgrid capacity with wind/light/firewood/storage and seawater desalination load[J].Journal of Electrotechnics, 2014, 29(02):102-112.
[3]段帅.含风/光/柴/蓄及海水淡化负荷的微电网优化调度方法[D].华北电力大学,2014.
[4] CHEN Y,LUH P B,GUAN C,et al. Short-term load forecasting:similar day-based wavelet neural networks[J].IEEE Transactions on Power Systems,2010, 25(1):322-330.
[5] CUI M J, KE D P, SUN Y Z, et al. Wind power ramp events forecasting using a stochastic scenario generation method[J]. IEEE Transactions on Sustainable Energy,2015, 6(2):422-433.
[6]林顺福,郝朝,汤晓栋等.基于数据挖掘的楼宇短期负荷预测方法研究[J].电力系统保护与控制,2016,44(7):83-89.LIN Shunfu,HAO Zhao,TANG Xiaodong,et al. Research on short-term load forecasting method of buildings basedon data mining[J]. Power System Protection and Control,2016,44(7):83-89.
[7]杨尚宝.我国海水淡化产业发展述评2016[J].水处理技术,2017,43(10):1-3+6.YANG Shangbao. Review on the development of seawater desalination industry in China 2016[J]. Water Treatment Technology,2017,43(10):1-3+6.
[8] UNIVERSITY Y. The future of seawater desalination:energy, technology, and the environment.[J]. Science,2011, 333(6043):712-717.
[9]丁晓,孙虹,郑海雁,季聪,徐金玲,仲春林,熊政.基于配用电大数据的短期负荷预测[J].电力工程技术,2018,37(3):21-27.DING Xiao, SUN Hong, JI Cong, et al. Short-term load forecasting based on allocation of electricity big data[J].Power engineering technology, 2018,37(3):21-27.
[10] YU H, CHEN Y, HASSAN S G,et al. Prediction of the temperature in a Chinese solar greenhouse based on LSSVM optimized by improved PSO[J]. Computers&Electronics in Agriculture, 2016, 122:94-102.
[11] AHMADI, ALI M. Toward reliable model for prediction drilling fluid density at wellbore conditions:A LSSVM model[J]. Neurocomputing, 2016, 211:143-149.
[12] CAO H Q, XU J, KE D P, et al. Economic dispatch of micro-grid based on improved particle-swarm optimization algorithm[C]. North American Power Symposium(NAPS), Denver, CO, USA, Sep. 18-20,2016.
[13]梁承红,姜宏,邢红宏.反渗透海水淡化技术的发展与应用[J].海军航空工程学院学报,2007, 22(4):494-496.LIANG Chenhong, JIANG Hong, XING Honghong.Development and application of reverse osmosis seawater desalination technology[J]. Journal of Naval Aeronautical Engineering Institute, 2007, 22(4):494-496.
[14]叶晓琰,佘旭南,胡敬宁,等.年产万吨级海水淡化高压泵关键技术研究与工程应用[J].水处理技术,2015(10):95-99.YE Xiaoyan, YU Xunan, HU Jingyu, et al. Key technology research and engineering application of annual production of 10, 000-ton seawater desalination high pressure pump[J]. Water Treatment Technology, 2015(10):95-99.
[15]刘文霞,徐晓波,周樨.基于支持向量机的纯电动公交车充/换电站日负荷预测[J].电力自动化设备,2014, 34(11):41-47.LIU Wenxia,XU Xiaobo,ZHOU Xi. Daily load forecasting of pure electric bus charging/changing station based on support vector machine[J]. Power Automation Equipment,2014, 34(11):41-47.
[16]张平,潘学萍,薛文超.基于小波分解模糊灰色聚类和BP神经网络的短期负荷预测[J].电力自动化设备,2012, 32(11):121-125.ZHANG Ping, PAN Xueping,XUE Wenchao. Short-term load forecasting based on wavelet decomposition and fuzzy grey clustering and BP neural network[J]. Power Automation Equipment, 2012, 32(11):121-125.
[17]李鑫滨,张娟,张岩,等.基于D-S证据理论的相似日支持向量机短期负荷预测[J].电网技术,2010(7):143-147.LI Xinbin, ZHANG Juan, ZHANG Yan, et al. Short-term load forecasting of similar daily support vector machines based on D-S evidence theory[J]. Power Grid Technology,2010(7):143-147.
[18]莫维仁,张伯明,孙宏斌,等.短期负荷预测中选择相似日的探讨[J].清华大学学报(自然科学版),2004, 44(1):106-109.MO Weiren, ZHANG Boming, SUN Hongbin, et al.Discussion on selecting similar days in short-term load forecasting[J]. Journal of Tsinghua University(Natural Science Edition), 2004, 44(1):106-109.
[19]刘梦良,刘晓华,高荣.基于相似日小波支持向量机的短期电力负荷预测[J].电工技术学报,2006, 21(11):59-64.LIU Mengliang, LIU Xiaohua, GAO Rong. Short-term load forecasting based on similar daily wavelet support vector machine[J]. Journal of Electrotechnics, 2006, 21(11):59-64.
[20]汲国强,汪鸿,王梦,陈建华,单体华,宋宗耘.基于大用户行为属性挖掘和LS-SVM的钢铁行业用电量预测研究[J].智慧电力,2018,46(9):60-65.JI Guoqiang, WANG Hong, WANG Meng, et al. Research on electricity consumption forecast of steel industry based on large user behavior attribute mining and LS-SVM[J].Smart Power,2018,46(9):60-65.
[21] SHEN X, CHEN F, HE T, et al. A new dynamical particle swarm optimization based on principle free entropy minimization[C].Tianjin:Fifth International Conference on Natural Computation, 2009,14-16.