Short-Term Load Forecasting Model Based on Online Sequential Extreme Support Vector Regression

被引：0
|
作者：
Jiang M. [1 ]
Gu D. [1 ]
Kong J. [1 ]
Tian Y. [2 ]
机构：
[1] Key Laboratory of Advanced Process Control for Light Industry (Jiangnan University), Wuxi, 214122, Jiangsu Province
[2] School of Electrical Engineering, Xinjiang University, Urumchi, 830047, Xinjiang Uygur Autonomous Region
来源：
Jiang, Min (minjiang@jiangnan.edu.cn) | 2018年 / Power System Technology Press卷 / 42期
基金：
中国国家自然科学基金;
关键词：
Online sequential extreme support vector regression model; Recursive feature selection; Short-term load forecasting; Simplified particle swarm optimization;
D O I：
10.13335/j.1000-3673.pst.2017.2400
中图分类号：
学科分类号：
摘要：
Load forecast becomes more important because of development of electricity markets and promotion of smart grid technologies. Accurate forecast results help to improve power system efficiency, reduce operating cost and cut down occurrence of power interruption events. Given high rate of the volume of high-dimension data, effective and accurate online forecast model is the emphasis of current research. For incrementally arriving data, conventional prediction methods need to retrain the model with all data repeatedly. Thus, adding a new data point in these models is computationally rather expensive and inefficient. To overcome this defect, this paper presents a short-term load forecast (STLF) model based on online sequential extreme support vector regression (OS- ESVR) algorithm. Firstly, recursive feature elimination method based on random forest model (RF-RFE) is used to automatically choose input variables of lagging loads. Secondly, filtered feature collection is input to train the OS- ESVR model. Simplified particle swarm optimization (SPSO) algorithm is adopted to optimize initial parameters. Finally, the proposed model is evaluated on STLF task. Case study based on ISO database of actual electric consumption in New England shows that the proposed STLF model possesses ability to be dynamically updated with new arriving data. The reported results clearly show superiority of the proposed scheme over all considered methods both in timeliness and accuracy. © 2018, Power System Technology Press. All right reserved.
引用
收藏
页码：2240 / 2247
页数：7
相关论文
共 18 条
  • [1] Kang C., Xia Q., Zhang B., A survey of power system load forecasting and development, Automation of Electric Power Systems, 28, 17, pp. 1-11, (2004)
  • [2] Pei D., Research and analysis of power system load forecasting, China Science and Technology, 7, 24, (2014)
  • [3] Yuan X., Wang C., Zhang C., Et al., A survey of short-term load forecasting methods in electric power systems, Electrical Automation, 26, 6, pp. 3-6, (2004)
  • [4] Wan K., Liu R., Application of interval time-series vector autoregressive model in short-term load forecasting, Power System Technology, 36, 11, pp. 77-81, (2012)
  • [5] Meng A., Hu H., Liu X., Short-term load forecasting using neural network based on wavelets and crisscross optimization algorithm, Power System Protection and Control, 44, 7, pp. 102-106, (2016)
  • [6] Liu W., Fu X., Wang L., Et al., WNN interval estimation algorithm for electric load forecasting based on threshold multi- frequency unscented Kalman filter, Power System Technology, 40, 2, pp. 527-533, (2016)
  • [7] Yu H., Zhang F., Short-term load forecasting based on fuzzy neural network, Power System Technology, 31, 3, pp. 68-72, (2007)
  • [8] Li X., Wang X., Zheng Y., Et al., Short-term wind load forecasting based on improved LSSVM and error forecasting correction, Power System Protection and Control, 43, 11, pp. 63-69, (2015)
  • [9] Xie M., Deng J., Ji X., Et al., Cooling load forecasting method based on support vector machine optimized with entropy and variable accuracy roughness set, Power System Technology, 41, 1, pp. 210-214, (2017)
  • [10] Li D., Yan Z., Yao L., Et al., Short-term load forecasting based on improved manifold regularization extreme learning machine, High Voltage Engineering, 42, 7, pp. 2092-2099, (2016)
12