Electrical Load Forecasting Using An Expanded Kalman Filter Bank Methodology

In previous work, a novel KFB24 strategy was first applied to track the key characteristics of the variable wind speed, solar irradiance and ambient air temperature in forecasting the expected wind and solar PV power output for micro-grid electrical power networks. Here, the KFB24 is expanded to a more accurate novel KFB 168 for the purpose of mapping and deriving predictions of the weekly electrical load demand profile in scheduling electrical power resources. Key results along with Statistical Hypothesis testing are presented to validate and substantiate the proposed KFB strategies and the accuracy of their prediction outputs.