Applying Deep Learning to the Heat Production Planning Problem in a District Heating System

Abstract

District heating system is designed to minimize energy consumption and environmental pollution by employing centralized production facilities connected to demand regions. Traditionally, optimization based algorithms were applied to the heat production planning problem in the district heating systems. Optimization-based models provide near optimal solutions, while it takes a while to generate solutions due to the characteristics of the underlying solution mechanism. When prompt re-planning due to any parameter changes is necessary, the traditional approaches might be inefficient to generate modified solutions quickly. In this study, we developed a two-phase solution mechanism, where deep learning algorithm is applied to learn optimal production patterns from optimization module. In the first training phase, the optimization module generates optimal production plans for the input scenarios derived from operations history, which are provided to the deep learning module for training. In the second planning phase, the deep learning module with trained parameters predicts production plan for the test scenarios. The computational experiments show that after the training process is completed, it has the characteristic of quickly deriving results appropriate to the situation. By combining optimization and deep learning modules in a solution framework, it is expected that the proposed algorithm could be applied to online optimization of district heating systems.