NEXT-HOUR ELECTRICITY PRICE FORECASTING USING LEAST SQUARES SUPPORT VECTOR MACHINE AND GENETIC ALGORITHM

Predicting the price of electricity is crucial for operation power systems. Short-term forecasting deals with forecasts from an hour to a day ahead. Hourly-ahead offer expected prices market participants before hours. This especially useful effective bidding strategies where amount can be reviewed or changed Nevertheless, many existing models have relatively low prediction accuracy. Furthermore, single are typically less accurate different scenarios. Thus, hybrid model comprising least squares support vector machine (LSSVM) and genetic algorithm (GA) was developed in this work predict higher tested on Ontario market. The inputs, which were hourly (HOEP) demand previous seven days, as well 1-h pre-dispatch (PDP), optimized by GA prevent losing potentially important inputs. At same time, LSSVM parameters obtain forecasts. LSSVM-GA shown produce average mean absolute percentage error (MAPE) 8.13% structure complex compared other studies. due fact that only two algorithms used (LSSVM GA), load HOEP week preceding Based results, it concluded proposed promising alternative good