Hybrid adaptive neuro-fuzzy inference system (ANFIS) for a multi-campus university energy consumption forecast

Research output: Contribution to journalArticlepeer-review

29 Citations (Scopus)


This study compares the performance of standalone adaptive neuro-fuzzy inference system (ANFIS) and its hybrid with particle swarm optimisation (PSO) in predicting the energy consumption from climatic factors for a multi-campus institution in South Africa. Monthly weather condition datasets (average wind speed, average maximum temperature, average minimum temperature, average dew point and average relative humidity) for 36 months were mapped with the corresponding monthly energy consumption for each campus as the model inputs and output respectively. The ANFIS and ANFIS-PSO models were trained and tested with 70% and 30% of the dataset respectively. The root mean square error (RMSE), mean absolute deviation (MAD), mean absolute percentage error (MAPE) and the computational time were used to evaluate the model for the four campuses. The ANFIS standalone model developed for campus C outperforms other standalone models for campus A, B and D with the following performance indices: RMSE = 1.27, MAD = 1.01, MAPE = 13.34, computational time = 14.61 secs. On the contrary, the ANFIS-PSO model developed for campus D outperforms both the standalone and the hybrid models for campus A, B and C with the following values of performance indices except for computational time: RMSE = 0.147, MAD = 0.125, MAPE = 2.89, computational time = 95.60 secs. This study concludes that tuning ANFIS parameters with PSO offers a better prediction accuracy, which is reliable for strategic energy planning, though at a higher computational time.

Original languageEnglish
Pages (from-to)1685-1694
Number of pages10
JournalInternational Journal of Ambient Energy
Issue number1
Publication statusPublished - 2022


  • Adaptive neuro-fuzzy inference system
  • energy forecast
  • multi-campus energy consumption
  • particle swarm optimisation

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • Building and Construction


Dive into the research topics of 'Hybrid adaptive neuro-fuzzy inference system (ANFIS) for a multi-campus university energy consumption forecast'. Together they form a unique fingerprint.

Cite this