Forecasting Model for Saturated Load Based on Chaotic Particle Swarm Optimization-Gaussian Process Regression

被引：0

作者：

Peng H. ^{[1
]}

Gu J. ^{[1
]}

Hu Y. ^{[1
]}

Song B. ^{[2
]}

机构：

[1] School of Electronic Information and Electrical Engineering, Research Center for Big Data Engineering and Technologies, Shanghai Jiao Tong University, Shanghai

[2] State Grid Corporation of East China, Shanghai

来源：

Gu, Jie (gujie@sjtu.edu.cn) | 1600年 / Automation of Electric Power Systems Press卷 / 41期

关键词：

Chaotic particle swarm optimization; Gaussian process regression; Load forecasting; Probabilistic forecasting; Saturated load;

D O I：

10.7500/AEPS20170119007

中图分类号：

学科分类号：

摘要：

Saturated load forecasting could effectively estimate future direction and final scale of the regional power grid, providing guidance for planning and mid/long-term transactions of the power market. Firstly, a probabilistic forecasting model based on Gaussian process regression (GPR) is adopted for saturated load forecasting, aiming at its characteristic of strong uncertainty and large time span. Secondly, the optimal solution of model hyper-parameters with the objective of minimizing the sum of squares due to errors (SSE) is realized by a modified chaotic particle swarm optimization (MCPSO) presented. In consideration of the randomness of the factors influencing the saturated load, a saturated load forecasting model based on modified chaotic particle swarm optimization-Gaussian process regression is proposed. Thirdly, in multi-scenarios using the above model while taking saturation criterion into account could forecast the saturated load and obtain multi-scenario scale and time-point. Finally, case studies show that this model not only has high precision, but also enhances the elasticity of forecasting results. © 2017 Automation of Electric Power Systems Press.

引用

页码：25 / 32and155

共 21 条

[1]

Xiao X., Zhou Y., Zhang N., Et al., Survey of saturated load analysis technology for urban power system and its application, Electric Power Automation Equipment, 34, 6, pp. 146-152, (2014)

[2]

Jia Y., Li S., Tan Y., Et al., Improved parametric estimation of logistic model for saturated load forecast, Power and Energy Engineering Conference, pp. 1-4, (2012)

[3]

Bao Z., Li S., Zhao F., Et al., Improved logistic model for saturated load forecast, Proceedings of the CSU-EPSA, 26, 11, pp. 7-11, (2014)

[4]

Shang F., Yang Z., Cheng H., Et al., Application of improved Verhulst model in saturation load forecasting, Proceedings of the CSU-EPSA, 27, 1, pp. 66-68, (2015)

[5]

Zhang J., Liu J., Chen Y., Et al., Saturated load forecasting based on per capita electricity consumption and per capita electricity load, East China Electric Power, 42, 4, pp. 661-664, (2014)

[6]

Tan Z., Zhang J., Wu L., Et al., A model integrating econometric approach with system dynamics for long-term load forecasting, Power System Technology, 35, 1, pp. 186-190, (2011)

[7]

Xiao B., Zhou C., Mu G., Review and prospect of the spatial load forecasting methods, Proceedings of the CSEE, 33, 25, pp. 78-92, (2013)

[8]

Liang J., Xia Q., A new method of long-term load forecasting based on scalar field analysis, Automation of Electric Power Systems, 33, 17, pp. 91-95, (2009)

[9]

Vasquez-Arnez R.L., Jardini J.A., Casolari R., Et al., A methodology for electrical energy forecast and its spatial allocation over developing boroughs, 2008 IEEE/PES Transmission and Distribution Conference and Exposition, pp. 1-6, (2008)

[10]

Li Y., Han D., Yan Z., Et al., Saturated load forecasting model under complex urbanization characteristics, Power System Technology, 40, 9, pp. 2824-2831, (2016)

← 1 2 3 →