Multivariate empirical mode decomposition based hybrid model for day-ahead peak load forecasting

Accurate day-ahead peak load forecasting is crucial not only for power dispatching but also has a great interest to investors and energy policy maker as well government. Literature reveals that 1% error drop of forecast can reduce 10 million pounds operational cost. Thus, this study proposed novel hybrid predictive model built upon multivariate empirical mode decomposition (MEMD) support vector regression (SVR) with parameters optimized by particle swarm optimization (PSO), which able capture precise electricity load. The novelty mainly comes from the application MEMD, enables data effectively extract inherent information among relevant variables at different time frequency during deterioration over time. Two real-world sets New South Wales (NSW) Victoria (VIC) in Australia have been considered verify superiority MEMD-PSO-SVR model. quantitative comprehensive assessments are performed, results indicate method promising alternative forecasting.