Time Series Analysis, Forecasting and Control
Time Series Analysis, Forecasting and Control
Innovative strategy of SOMA control parameter setting
NNECFSIC'12 Proceedings of the 12th WSEAS international conference on Neural networks, fuzzy systems, evolutionary computing & automation
Neural network synthesis via asynchronous analytic programming
NNECFSIC'12 Proceedings of the 12th WSEAS international conference on Neural networks, fuzzy systems, evolutionary computing & automation
ANN synthesis for an agglomeration heating power consumption approximation
ACMOS'11 Proceedings of the 13th WSEAS international conference on Automatic control, modelling & simulation
Neural network synthesis dealing with classification problem
ACMOS'11 Proceedings of the 13th WSEAS international conference on Automatic control, modelling & simulation
Hi-index | 0.00 |
In order to improve the control level of district-heating systems, it is necessary for the energy companies to have reliable optimization routines, implemented in their organizations. However, before a plan of heat production, a prediction of the heat demand first needs to be determined. Forecast of this heat demand course is significant for short-term and long-term planning of heat production. This forecast is most important for technical and economic consideration. In this paper we propose the forecast model of heat demand based on the Box-Jenkins methodology. The model is based on the assumption that the course of DDHD can be described sufficiently well as a function of the outdoor temperature and the weather independent component (social components). Time of the day affects the social components. The time dependence of the load reflects the existence of a daily heat demand pattern, which may vary for different week days and seasons. Forecast of social component is realized by means of Box-Jenkins methodology. This model is used for prediction of heat demand in different locality. The results of heat demand prediction in specific locality and conclusions are presented.