Using PSO and Genetic algorithms to optimize ANFIS model for forecasting Uganda’s net electricity consumption

Creative Commons License

Kasule A., Ayan K.

Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi, vol.24, no.2, pp.324-337, 2020 (National Refreed University Journal)

  • Publication Type: Article / Article
  • Volume: 24 Issue: 2
  • Publication Date: 2020
  • Doi Number: 10.16984/saufenbilder.629553
  • Title of Journal : Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi
  • Page Numbers: pp.324-337


Uganda seeks to transform its society from a peasant to a modern and largely urban society by

the year 2040. To achieve this, electricity as a form of modern and clean energy has been

identified as a driving force for all the sectors of the economy. For this reason, electricity

consumption forecasts that are realistic and accurate are key inputs to policy making and

investment decisions for developing Uganda’s electricity sector. In this study, we present an

ANFIS long-term electricity forecasting model that is easy to interpret. We use the model to

forecast Uganda’s electricity consumption. The ANFIS model takes population, gross domestic

product, number of subscribers and average electricity price as input variables and electricity

consumption as the output. We use particle swarm optimization (PSO) algorithm and genetic

algorithm (GA) to optimize the parameters of the model. A forecast accuracy of 94.34% is

achieved for GA-ANFIS, while 90.88% accuracy is achieved for PSO-ANFIS as compared to

87.79% for multivariate linear regression (MLR) model. Comparison with official forecasts

made by Ministry of Energy and Mineral Development (MEMD) revealed low forecast errors.