Forecasting model of residential load based on general regression neural network and PSO-Bayes least squares support vector machine

Abstract

Firstly, general regression neural network (GRNN) was used for variable selection of key influencing factors of residential load (RL) forecasting. Secondly, the key influencing factors chosen by GRNN were used as the input and output terminals of urban and rural RL for simulating and learning. In addition, the suitable parameters of final model were obtained through applying the evidence theory to combine the optimization results which were calculated with the PSO method and the Bayes theory. Then, the model of PSO-Bayes least squares support vector machine (PSO-Bayes-LS-SVM) was established. A case study was then provided for the learning and testing. The empirical analysis results show that the mean square errors of urban and rural RL forecast are 0.02% and 0.04%, respectively. At last, taking a specific province RL in China as an example, the forecast results of RL from 2011 to 2015 were obtained.

Keywords

residential load / load forecasting / general regression neural network (GRNN) / evidence theory / PSO-Bayes least squares support vector machine

References

[1] SongK. B., HaS. K.. Hybrid load forecasting method with analysis of temperature sensitivities [J]. Transactions on Power Systems, 2006, 21(2): 869-877

[2] LutzenhiserL.. Social and behavioral aspects of energy use [J]. Annual Review of Energy and the Environment, 1993, 18: 247-289

[3] SongK. B., BaekyS., HongD. H., JangG.. Short-term load forecasting for the holidays using fuzzy linear regression method [J]. Transactions on Power Systems, 2005, 20(1): 96-102

[4] CHO M Y, HWANG J C, CHEN C S. Customer short term load forecasting by using ARIMA transfer function model [C]// EMPD International Conference on Energy Management and Power Deliver. Singapore, 1995: 317–322.

[5] BeccaliM., CelluraM., BranoV. L., MarvugliaA.. Short-term prediction of household electricity consumption: Assessing weather sensitivity in a Mediterranean area [J]. Renewable and Sustainable Energy Reviews, 2008, 12(8): 2040-2065

[6] BoukaryO.. Household energy preferences for cooking in urban Ouagadougou Burkina Faso [J]. Energy Policy, 2006, 34(18): 3787-3795

[7] HoltedahlP., JoutzF. L.. Residential electricity demands in Taiwan [J]. Energy Economics, 2004, 26(2): 201-224

[8] HalvorsenB., LarsenB. M.. The flexibility of household electricity demand over time [J]. Resource and Energy Economics, 2001, 23(1): 1-18

[9] YingL.-C., PanM.-chiu.. Using adaptive network based fuzzy inference system to forecast regional electricity load [J]. Energy Conversion and Management, 2008, 49(2): 205-211

[10] BernardJ. T., BolducD., YameogoN. D.. A pseudo-panel data model of household electricity demand [J]. Resource and Energy Economics, 2011, 33(1): 315-325

[11] MandalP., SenjyuT., FunabashiT.. Neural networks approach to forecast several hour ahead electricity prices and loads in deregulated market [J]. Energy Conversion and Management, 2006, 47(15/16): 2128-2142

[12] HongW.-c.. Electric load forecasting by support vector model [J]. Applied Mathematical Modeling, 2009, 33(5): 2444-2454

[13] HUANG Yue, LI Dan, GAO Li-qun, WANG Hong-yuan. A short-term load forecasting approach based on support vector machine with adaptive particle swarm optimization algorithm [C]// Chinese Control and Decision Conference. Guilin, China, 2009: 1448–1453.

[14] MIRHOSSEINI M, MARZBAND M, OLOOMI M. Short term load forecasting by using neural network structure [C]// ECTI-CON International Conference. Chonburi, Thailand, 2009: 240–243.

[15] WuQi.. Product demand forecasts using wavelet kernel support vector machine and particle swarm optimization in manufacture system [J]. Journal of Computational and Applied Mathematics, 2010, 233(10): 2481-2491

[16] WuQi.. Power load forecasts based on hybrid PSO with Gaussian and adaptive mutation and Wv-SVM [J]. Expert Systems with Applications, 2010, 37(1): 194-201

[17] GaoC.-w., BompardE., NapoliR., ChengH.-zhong.. Price forecast in the competitive electricity market by support vector machine [J]. Physica A: Statistical Mechanics and its Applications, 2007, 382(1): 98-113

[18] NiuD.-x., WangY.-l., WuD. D.. Power load forecasting using support vector machine and ant colony optimization [J]. Expert Systems with Applications, 2010, 37(3): 2531-2539

[19] PolatO., YildirimT.. FPGA implementation of a general regression neural network: An embedded pattern classification system [J]. Digital Signal Processing, 2010, 20(3): 881-886

[20] SpechtD. F.. A general regression neural network [J]. IEEE Transactions on Neural Networks, 1991, 2(6): 568-576

[21] YanW.-w., ShaoH.-h., WangX.-fan.. Soft sensing modeling based on support vector machines and Bayesian model selection [J]. Computers and Chemical Engineering, 2004, 28(8): 1489-1498

[22] Shangdong Province Statistical Bureau.Shandong Statistical Yearbook [M], 2009, Beijing, China Statistics Press: 29-30