Authors: Meiping Wang; Qi Tian
Addresses: College of Environment Science and Engineering, Taiyuan University of Technology, Taiyuan, China ' College of Environment Science and Engineering, Taiyuan University of Technology, Taiyuan, China
Abstract: In order to improve operational efficiency of district-heating systems, it is necessary for the energy companies to have reliable optimisation routines to realise the intelligent processing of the heating system. However, before a production plan for the heat-producing units can be constructed, a prediction of the heat demand firstly needs to be determined. The outdoor temperature together with the characteristic of heating system has the greatest influence on the heat supply. This is also the core of the load prediction model developed in the paper. A dynamic model of heating system is presented, in which wavelet analysis is combined with neural network on the basis of the analysis of many factors. The model is trained and tested with measured values of 128 days from a heat producer. The results from this simulation were then compared with results from alternative methods found in literatures. It is shown that the approach has more satisfactory tracking performance and higher accuracy than the other two algorithms. It is applicable for short-term thermal load forecast.
Keywords: wavelet analysis; neural networks; thermal load forecasting; district heating; operational efficiency; optimisation; heating systems; dynamic modelling; simulation.
International Journal of Wireless and Mobile Computing, 2013 Vol.6 No.6, pp.608 - 614
Received: 24 May 2013
Accepted: 01 Jul 2013
Published online: 12 Nov 2013 *