Application of least absolute value parameter estimation technique based on linear programming to short-term load forecasting

Short term load forecasting employs load models that express the effects of influential variables on system load. The model coefficients are found by fitting the load model to a database of previous load and observations of the variables, and then solving the resulting overdetermined system of equations. This study compares two linear static parameter estimation techniques as they apply to the twenty-four hour off-line forecasting problem. Here a least squares and a least absolute value based linear programming algorithm is used to simulate the forecast response of three twenty-four hour off-line load models. The three load models are: (1) a multiple linear regression model; (2) a harmonic decomposition model; and (3) a hybrid multiple linear regression/harmonic decomposition model. The results obtained for each estimation algorithm via each load model, using the same databases and forecasting periods are presented.