Forecasting Short-term Electricity Demand in Residential Sector Based on Support Vector Regression and Fuzzy-rough Feature Selection with Particle Swarm Optimization

Abstract The aim of this study is to provide a precise model for one-month-ahead forecast of electricity demand in residential sector. In this study, a total of 20 influential variables are taken into account including monthly electricity consumption, 14 weather variables, and 5 social variables. Based on support vector regression and fuzzy-rough feature selection with particle swarm optimization algorithms, the proposed method established a model with variables that relate to the forecast without ignoring some of these variables one may inevitably lead to forecasting errors. The proposed forecasting model was validated using historical data from South Korea. Its time period was from January 1991 to December 2012. The first 240 months were used for training and the remaining 24 for testing. The performance was evaluated using MAPE, MAE, RMSE, MBE, and UPA values. Furthermore, it was compared with that obtained from the artificial neural network, auto-regressive integrated moving average, multiple linear regression models, and the methods proposed in the previous studies, and found superior for every performance measure considered in this study. The proposed method has an advantage over the previous methods because it automatically determines appropriate and necessary variables for a reliable forecast. It is expected that the proposed model can contribute to more accurate forecasting of short-term electricity demand in residential sector. The ability to accurately forecast short-term electricity demand can assist power system operators and market participants in ensuring sustainable electricity planning decisions and secure electricity supply to the consumers.

[1]  J. C. Lam,et al.  Seasonal variations in residential and commercial sector electricity consumption in Hong Kong , 2008 .

[2]  Xiangyang Wang,et al.  Feature selection based on rough sets and particle swarm optimization , 2007, Pattern Recognit. Lett..

[3]  S. M. Al-Alawi,et al.  Principles of electricity demand forecasting. II. Applications , 1997 .

[4]  V. Ismet Ugursal,et al.  Modeling of end-use energy consumption in the residential sector: A review of modeling techniques , 2009 .

[5]  E. Georgopoulou,et al.  Models for mid-term electricity demand forecasting incorporating weather influences , 2006 .

[6]  Ali Azadeh,et al.  An integrated simulation-based fuzzy regression-time series algorithm for electricity consumption estimation with non-stationary data , 2011 .

[7]  Pei-Chann Chang,et al.  Monthly electricity demand forecasting based on a weighted evolving fuzzy neural network approach , 2011 .

[8]  Spyros Makridakis,et al.  Accuracy measures: theoretical and practical concerns☆ , 1993 .

[9]  Xiangyang Wang,et al.  Rough set feature selection and rule induction for prediction of malignancy degree in brain glioma , 2006, Comput. Methods Programs Biomed..

[10]  Xindong Wu,et al.  Support vector machines based on K-means clustering for real-time business intelligence systems , 2005, Int. J. Bus. Intell. Data Min..

[11]  Chusak Limsakul,et al.  The Comparision of Mid Term Load Forecasting between Multi-Regional and Whole Country Area Using Artificial Neural Network , 2010 .

[12]  Alessandra Bassini,et al.  Relationships between meteorological variables and monthly electricity demand , 2012 .

[13]  Jianzhou Wang,et al.  A trend fixed on firstly and seasonal adjustment model combined with the ε-SVR for short-term forecasting of electricity demand , 2009 .

[14]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[15]  Harun Kemal Ozturk,et al.  Modeling and prediction of Turkey’s electricity consumption using Artificial Neural Networks , 2009 .

[16]  Chris Cornelis,et al.  A noise-tolerant approach to fuzzy-rough feature selection , 2008, 2008 IEEE International Conference on Fuzzy Systems (IEEE World Congress on Computational Intelligence).

[17]  H. Raman,et al.  Multivariate modelling of water resources time series using artificial neural networks , 1995 .

[18]  T. Yalcinoz,et al.  Short term and medium term power distribution load forecasting by neural networks , 2005 .

[19]  M. Z. Dauhoo,et al.  Forecasting of peak electricity demand in Mauritius using the non-homogeneous Gompertz diffusion process , 2011 .

[20]  Xiao-Jun Zeng,et al.  Short-Term and Midterm Load Forecasting Using a Bilevel Optimization Model , 2009, IEEE Transactions on Power Systems.

[21]  Kelvin K. W. Yau,et al.  Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks , 2007 .

[22]  Ching-Lai Hor,et al.  Analyzing the impact of weather variables on monthly electricity demand , 2005, IEEE Transactions on Power Systems.

[23]  Lon-Mu Liu,et al.  Identification of multiple-input transfer function models , 1982 .

[24]  Zeguo Qiu,et al.  Electricity Consumption Prediction based on Data Mining Techniques with Particle Swarm Optimization , 2013 .

[25]  D. Sailor,et al.  Sensitivity of electricity and natural gas consumption to climate in the U.S.A.—Methodology and results for eight states , 1997 .

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

[27]  Galip Altinay,et al.  Electricity consumption and economic growth: evidence from Turkey , 2005 .

[28]  Afsoon Moaref,et al.  A particle swarm optimization based on a ring topology for fuzzy-rough feature selection , 2013, 2013 13th Iranian Conference on Fuzzy Systems (IFSC).

[29]  Qiang Shen,et al.  New Approaches to Fuzzy-Rough Feature Selection , 2009, IEEE Transactions on Fuzzy Systems.

[30]  E. Tserkezos.  Forecasting residential electricity consumption in Greece using monthly and quarterly data , 1992 .

[31]  Karoliina Pilli-Sihvola,et al.  Climate change and electricity consumption--Witnessing increasing or decreasing use and costs? , 2010 .

[32]  Robert G. Quayle,et al.  Heating Degree Day Data Applied to Residential Heating Energy Consumption , 1980 .

[33]  M. Thatcher.  Modelling changes to electricity demand load duration curves as a consequence of predicted climate change for Australia , 2007 .

[34]  J. Razmi,et al.  Forecasting electricity consumption by clustering data in order to decline the periodic variable’s affects and simplification the pattern , 2009 .

[35]  Saleh M. Al-Alawi,et al.  Forecasting monthly electric load and energy for a fast growing utility using an artificial neural network , 1995 .

[36]  Chusak Limsakul,et al.  Multi-substation control central load area forecasting by using HP-filter and double neural networks (HP-DNNs) , 2013 .

[37]  Xiaojia Wang.  Forecasting Modeling and Analysis of Power Engineering in China Based on Gauss-Chebyshev Formula , 2012 .

[38]  R.B. Misra,et al.  A Novel Approach of Input Variable Selection for ANN Based Load Forecasting , 2008, 2008 Joint International Conference on Power System Technology and IEEE Power India Conference.

[39]  Wei-Chiang Hong,et al.  Electric load forecasting by seasonal recurrent SVR (support vector regression) with chaotic artific , 2011 .

[40]  Zhiqiang Chen,et al.  PLS-SVR Optimized by PSO Algorithm for Electricity Consumption Forecasting , 2013 .

[41]  Chris Cornelis,et al.  Feature Selection with Fuzzy Decision Reducts , 2008, RSKT.

[42]  Ahmed Z. Al-Garni,et al.  Modelling and forecasting monthly electric energy consumption in eastern Saudi Arabia using abductive networks , 1997 .

[43]  Enric Valor,et al.  Daily Air Temperature and Electricity Load in Spain , 2001 .

[44]  J. C. Lam.  Climatic and economic influences on residential electricity consumption , 1998 .

[45]  Sven F. Crone,et al.  Forecasting with Computational Intelligence - An Evaluation of Support Vector Regression and Artificial Neural Networks for Time Series Prediction , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.