A systematic review on the methods of short term load forecasting

Load forecasting is always required for the planning and extension of power system. With the emergence of smart grid, forecasting of load and its management has been a primal concern for a researcher. Load forecasting has been challenging not only for developing countries but also for developed and industrialized nations. The main problems for developing nations are missing necessary data, appropriate load forecasting models and required institutions, these limitations are somewhat less serious for developed nations. Due to limitations in the model structure and missing data forecasted energy demands are often found to deviate from the actual demands. This paper contains a systematic review on the methods of load forecasting which is done on the basis of 126 research papers and the best methods for load forecasting on the basis of time, inputs, outputs and error type have been determined. The methods compared are time series analysis and machine learning algorithms. This meta-analysis has been defined to help researchers to take an effective decision by choosing the right model from their problem.