SHORT TERM LOAD FORECASTING USING GROUP METHOD OF DATA HANDLING OPTIMIZED BY ARTIFICIAL BEE COLONY TECHNIQUE
The need for stable, secure and cost-effective power requires a balance between supply and demand of electricity. Hence, the need for an effective and accurate forecasting technique to maintain continuous supply of stable power to consumers. The limitations of some common forecasting techniques such as Artificial Neural Network (ANN) and Support Vector Machine (SVM) are falling into local minimum, overfitting and computational complexity. This paper presents Short Term Load Forecasting (STLF) technique using Group Method of Data Handling (GMDH) optimized by Artificial Bee Colony (ABC) algorithm. Historical load data and weather data were used as input variables to the model using MATLAB software. Performance of the proposed technique was evaluated and compared with GMDH load forecasting technique. The Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) were employed to investigate the performance of the presented models. Four years load data and weather data collected from Transmission Company of Nigeria (TCN) and Nigerian Metrological Agency (NIMET) were used for training, testing and validation of the models. Results showed that GMDH and GMDH optimized by ABC recorded MAPE of 4.6633 and 4.2083 respectively while the RMSE of 1.6861 and 1.217 respectively. The results obtained showed that the GMDH optimized by ABC model has the lowest MAPE and RMSE when compared with GMDH. The evaluation results indicated that the GMDH-ABC model provides more accurate load forecasts compared to former model. Hence, this research showed that GMDH-ABC approach is more accurate and effective than GMDH STLF technique. It is recommended that further studies on this work should focus on employing other optimization algorithms to optimize GMDH model. Also, it is suggested that long term load forecasting model using GMDH-ABC be developed by incorporating additional parameters such as season of the year, GDP, population growth, festive period and holidays.
Authors : Musa, M., Hassan, A. and Hassan, S.M.
Category : Open Access Volume (Issue) : 10(1) Date Uploaded : 22nd May 2024