Machine learning based switching model for electricity load forecasting

In deregulated power markets, forecasting electricity loads is one of the most essential tasks for system planning, operation and decision making. Based on an integration of two machine learning techniques: Bayesian clustering by dynamics (BCD) and support vector regression (SVR), this paper proposes a novel forecasting model for day ahead electricity load forecasting. The proposed model adopts an integrated architecture to handle the non-stationarity of time series. Firstly, a BCD classifier is applied to cluster the input data set into several subsets by the dynamics of the time series in an unsupervised manner. Then, groups of SVRs are used to fit the training data of each subset in a supervised way. The effectiveness of the proposed model is demonstrated with actual data taken from the New York ISO and the Western Farmers Electric Cooperative in Oklahoma.

[1]  George E. P. Box,et al.  Time Series Analysis: Forecasting and Control , 1977 .

[2]  Paul R. Cohen,et al.  Bayesian Clustering by Dynamics Contents 1 Introduction 1 2 Clustering Markov Chains 2 , 2022 .

[3]  Rey-Chue Hwang,et al.  An adaptive modular artificial neural network hourly load forecaster and its implementation at electric utilities , 1995 .

[4]  J.A.P. Lopes,et al.  Load forecasting performance enhancement when facing anomalous events , 2005, IEEE Transactions on Power Systems.

[5]  J. Zbilut,et al.  Embeddings and delays as derived from quantification of recurrence plots , 1992 .

[6]  Gunnar Rätsch,et al.  Predicting Time Series with Support Vector Machines , 1997, ICANN.

[7]  Ming-Wei Chang,et al.  Load Forecasting Using Support Vector Machines: A Study on EUNITE Competition 2001 , 2004, IEEE Transactions on Power Systems.

[9]  Tomonobu Senjyu,et al.  Next day load curve forecasting using hybrid correction method , 2002, IEEE/PES Transmission and Distribution Conference and Exhibition.

[10]  J. Fox.  Applied Regression Analysis, Linear Models, and Related Methods , 1997 .

[11]  Carlos E. Pedreira,et al.  Neural networks for short-term load forecasting: a review and evaluation , 2001 .

[12]  Nima Amjady,et al.  Short-term hourly load forecasting using time-series modeling with peak load estimation capability , 2001 .

[13]  S. Muto,et al.  Regression based peak load forecasting using a transformation technique , 1994 .

[14]  R. Buizza,et al.  Neural Network Load Forecasting with Weather Ensemble Predictions , 2002, IEEE Power Engineering Review.

[15]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1972 .

[16]  T. Funabashi,et al.  Next day load curve forecasting using hybrid correction method , 2005, IEEE Transactions on Power Systems.

[17]  W. A. Pridmore,et al.  Comparative Models for Electrical Load Forecasting , 1986 .

[18]  Shyh-Jier Huang,et al.  Short-term load forecasting via ARMA model identification including non-Gaussian process considerations , 2003 .

[19]  M. K. Soni,et al.  Artificial Neural Network-Based Peak Load Forecasting Using Conjugate Gradient Methods , 2002, IEEE Power Engineering Review.

[20]  S. Fan,et al.  Short-term load forecasting based on an adaptive hybrid method , 2006, IEEE Transactions on Power Systems.

[21]  G. Jang,et al.  Short-term load forecasting for the holidays using fuzzy linear regression method , 2005, IEEE Transactions on Power Systems.

[22]  Paola Sebastiani,et al.  Clustering Continuous Time Series , 2001, ICML.

[23]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[24]  Shu Fan,et al.  Peak Load Forecasting Using the Self-organizing Map , 2005, ISNN.

[25]  David Infield,et al.  Optimal smoothing for trend removal in short term electricity demand forecasting , 1998 .

[26]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.