A comparative approach for modelling the cost of energy in sport facilities

Maintenance and running costs contribute significantly to the total cost of running facilities. Almost half of the energy consumed in the UK is used in buildings. Energy consumption can be attributed to many factors. Describes the fundamentals associated with modelling running costs in leisure centres and then investigates 19 sport centres in the city of Liverpool, using data elicited from the Liverpool Leisure Services Directorate. The energy operating costs were analysed using statistical techniques and artificial intelligence methods. Three types of modelling, linear/non‐linear regression, neural networks and neurofuzzy were developed to predict energy cost. Testing and validation of the results showed that neural network models outperformed both regression and neurofuzzy techniques. However, all the models showed a high level of accuracy. The models would be of use to professionals involved in feasibility studies.