Heat Load Numerical Prediction for District Heating System Operational Control

Abstract

To develop an advanced control of thermal energy supply for domestic heating, a number of new challenges need to be solved, such as the emerging need to plan operation in accordance with an energy market-based environment. However, to move towards this goal, it is necessary to develop forecasting tools for short- and long-term planning, taking into account data about the operation of existing heating systems. The paper considers the real operational parameters of five different heating networks in Latvia over a period of five years. The application of regression analysis for heating load dependency on ambient temperature results in the formulation of normalized slope for the regression curves of the studied systems. The value of this parameter, the normalized slope, allows describing the performance of particular heating systems. Moreover, a heat load forecasting approach is presented by an application of multiple regression methods. This short-term (day-ahead) forecasting tool is tested on data from a relatively small district heating system with an average load of 20 MW at ambient temperature of 0 °C. The deviations of the actual heat load demand from the one forecasted with various training data set sizes and polynomial orders are evaluated for two testing periods in January of 2018. Forecast accuracy is assessed by two parameters – mean absolute percentage error and normalized mean bias error.

Bayesian Optimization-Based LSTM for Short-Term Heating Load Forecasting

“…The various methods mentioned above provide scientific guidance for heat load prediction [15]. Among them, machine learning methods are more popular in heat load forecasting due to their high accuracy and flexibility [16]. Currently, machine learning has been applied to data mining, computer vision, natural language processing, and other fields [17].…”

Optimal Planning of Future District Heating Systems—A Review

“…Historically, regression techniques have been more frequently used for energy use prediction. In general, a correlation between energy use and weather conditions, such as ambient temperature, solar radiation, wind speed etc., as well as historical consumption data, is constructed to predict future energy use [48][49][50]. In [40,47], detailed reviews on regression models for energy use predictions were elaborated.…”

Environmental Impact of District Heating System Retrofitting

“…Precise and accurate prediction of heat demand is vital for DH operators. While short term heat load numerical prediction can be carried out using available statistic data [24], the current study is focused on long-term planning, where goals of national and EU energy policy and different socio-economic factors are taken into account. Planning of DH systems can be performed with different techniques, which are broadly presented in scientific literature [25][26][27].…”