Estimating the cost of energy usage in sport centres: A comparative modelling approach

The cost of provision and maintenance of safe and comfortable conditions for the activity taking place in any leisure centre are the predominant factors in the prediction of running costs. This paper describes the fundamentals associated with running costs in leisure centres and then investigates nineteen sport centres in the City of Liverpool, United Kingdom 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 neuro-fuzzy were developed to predict total energy cost. Testing and validation of the results showed that neural network models outperformed both regression and neuro-fuzzy techniques. However, all the models showed a high level of accuracy. The models would be of use to professionals involved in feasibility studies of different scenarios at the design stage.