Load Forecasting Model for Energy Management System using Elman Neural Network
Electric load forecasting is used for forecasting of future electric loads. Since the economy and reliability of operations of a power system are greatly affected by electric load, cost savings mainly depend on load forecasting accuracy. An accurate system load forecasting which is used to calculate short-term electric load forecasts, is an essential component of any Energy Management System (EMS). This can be improved by making use of Artificial Neural Networks (ANN). Existing Boosted Neural Networks (BooNN) technique helps in reduction of forecasting errors and variation in forecasting accuracy. However it is not flexible to rapid load changes.In the proposed work, Elman Neural Network technique is considered. This technique improves the load forecasting accuracy. The proposed method is implemented in IEEE 14 bus system. Simulation results showed that this method has increased the Voltage profile and also the active power losses have been reduced. Overall power transfer capability has been improved. Also the computational time has been minimized when compared to the existing techniques.