Heat load forecasting using adaptive temporal hierarchies

Heat load forecasts are crucial for energy operators in order to optimize the production at district heating plants coming hours. Furthermore, of heat needed optimized control network since a lower temperature reduces loss, but required supply end-users puts limit on level. Consequently, improving accuracy leads savings and reduced loss by enabling improved an schedule plant. This paper proposes use temporal hierarchies enhance heating. Usually, only made aggregation level that is most important system. However, multiple levels can be reconciled lead more accurate essentially all levels. Here it auto- cross-covariance between forecast errors different taken into account. suggests novel framework using adaptive estimation improve optimally combining from reconciliation process. The weights computed adaptively estimated covariance matrix with full structure, process share time-varying information both within case study shows proposed improves 15% compared commercial state-of-the-art operational forecasts.