Artificial immune simulation for improved forecasting of electricity consumption with random variations

This paper presents an integrated algorithm for forecasting annual electrical energy consumption based on Artificial Immune System (AIS), Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and computer simulation. Computer simulation is developed to generate random variables for annual electricity consumptions in selected countries. Most recent studies are concerned with deterministic data sets which could enhance relative error. However, this study utilizes fitted random variables as input data to decrease the relative error. Mean Absolute Percentage Error (MAPE) is used for evaluating the results and selecting the best forecasting model. To show the applicability of the proposed algorithm, the annual electricity consumptions for 16 countries from 1980 to 2006 are considered and the proposed algorithm is applied to the corresponding historical data. Three considered meta-heuristics (i.e. AIS, GA, and PSO) are compared with each other in estimation of electricity consumption in the selected countries. The comparison is made based on MAPE for the test period data. For the selected countries, AIS method with the Clonal Selection Algorithm (CLONALG) shows satisfactory results when applied with simulated data and has been selected as the preferred method. This is the first study that uses an integrated AIS-simulation for improved forecasting of electricity consumption with random variations.