Short-term Power Load Forecasting of Residential Community Based on GRU Neural Network

The power load of residential community has the characteristics of wild fluctuations, complex influence factors and difficult forecasting. To deal with that, a short-term load forecasting (STLF) method for residential community based on gated recurrent unit (GRU) neural network was proposed. The least absolute shrinkage and selection operator (Lasso) and partial correlation analysis are used to analyze the influence of temperature, humidity, rainfall and wind speed on the load. It shows that the average temperature affects the change of the load most among various factors, thus the average temperature is added as an input variable to the load forecasting model based on GRU network. The simulation results show that the proposed method is faster within the similar forecasting accuracy, compared with the long short-term memory (LSTM) network and traditional recurrent neural network (RNN). It’s proven to be a more effective residential community short-term load forecasting method.

[1]  Robert J. Marks,et al.  Electric load forecasting using an artificial neural network , 1991 .

[2]  L. Breiman.  Better subset regression using the nonnegative garrote , 1995 .

[3]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[4]  Wang Xi-fan.  A SUPPORT VECTOR MACHINE APPROACH FOR SHORT TERM LOAD FORECASTING , 2002 .

[5]  Tai Neng-ling.  NEW PRINCIPLE BASED ON WAVELET TRANSFORM FOR POWER SYSTEM SHORT-TERM LOAD FORECASTING , 2003 .

[6]  Yang Ji-wang.  Analysis and comparison of several electric load forecasting methods , 2004 .

[7]  Dug Hun Hong,et al.  Short-term load forecasting for the holidays using fuzzy linear regression method , 2005 .

[8]  Ni Yi-xin.  WAVELET ANALYSIS BASED ARIMA HOURLY ELECTRICITY PRICES FORECASTING APPROACH , 2005 .

[9]  Yi Wang,et al.  Enhancing short-term probabilistic residential load forecasting with quantile long–short-term memory , 2009 .

[10]  Cong Zhen.  Application Profiles of Support Vector Machine in Short-term Load Forecasting , 2011 .

[11]  Chen Yizhe,et al.  Active Control Strategy for Microgrid Energy Storage System Based on Short-Term Load Forecasting , 2011 .

[12]  Xue Wenchao.  Short-term load forecasting based on wavelet decomposition,fuzzy gray correlation clustering and BP neural network , 2012 .

[13]  Davide Anguita,et al.  Energy Load Forecasting Using Empirical Mode Decomposition and Support Vector Regression , 2013, IEEE Transactions on Smart Grid.

[14]  Xiaoping Li,et al.  Optimization algorithms for MISO polygonal fuzzy neural networks , 2015 .

[15]  Fathi M. Salem,et al.  Gate-variants of Gated Recurrent Unit (GRU) neural networks , 2017, 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS).