Effective management of district heating networks depends upon the correct forecasting of heat consumption during a certain period. In this work short-term forecasting for the amount of heat consumption is performed first to validate the three forecasting methods: partial least squares (PLS) method, artificial neural network (ANN), and support vector regression (SVR) method. Based on the results of short-term forecasting, one-week ahead forecasting was performed for the Suseo district heating network. Data of heat consumption and ambient temperature during January and February in 2007 and 2008 were employed as training elements. The heat consumption estimated was compared with actual one in the Suseo area to validate the forecasting models.

This paper presents an optimal management model for structural and operational optimization of an integrated district heating system (DHS) with multiple regional branches. A DHS consists of energy suppliers and consumers, district heating pipelines and heat storage facilities in a region. The integrated DHS considered in this paper consists of 11 regional DHS branches. In the optimal management system, production and consumption of heat, transport and storage of heat at each regional DHS are taken into account. The optimal management system is formulated as a mixed integer linear programming (MILP), where the objective is to minimize the overall cost or to maximize the profits of the integrated DHS by generating electricity while satisfying the operation constraints of heat units and networks, as well as fulfilling heating demands from consumers. Evaluation of the operation cost is based on daily operations for two months (during August and December) at each DHS located in Seoul and Gyeonggi-do in Korea. Results of numerical simulations show the increase of energy efficiency due to the introduction of the present optimal operation system.

A district heating system (DHS) consists of energy suppliers and consumers, heat generation and storage facilities and power transmission lines in the region. DHS has taken charge of an increasingly important role as the energy cost increases recently. In this work, a model for operational optimization of the DHS in the metropolitan area is presented by incorporating forecast for demand from customers. In the model, production and demand of heat in the region of Suseo near Seoul, Korea, are taken into account as well as forecast for demand using the artificial neural network. The optimization problem is formulated as a mixed integer linear programming (MILP) problem where the objective is to minimize the overall operating cost of DHS. The solution gives the optimal amount of network transmission and supply cost. The optimization system coupled with forecast capability can be effectively used as design and longterm operation guidelines for regional energy policies.

This paper presents a scheme to achieve structural and operational optimization for the heat plant in a district energy system. A district energy system consists of energy suppliers and consumers, district heating pipelines and heat storage facilities in a region. Production and consumption of energy and transport of energy as well as storage of heat are taken into account in the model. The problem is formulated as a mixed integer linear programming (MILP) problem where the objective is to minimize the overall cost of the district energy system. Evaluation of the energy production cost is based on the daily operation for every season at the plant located at Suseo in Seoul, Korea. From the results of numerical simulations we can see that the district energy system is well approximated by the proposed model, and that the energy efficiency is improved by the application of the optimal operation conditions provided by the proposed model.