| Popis: |
This paper proposes an optimization method on energy consumption for public buildings based on the data-driven heuristic dynamic programming algorithm. To this end, a large amount of building data is first collected from a well-established monitoring system, including electricity, environmental information and human behaviors. According to this, the model network of HDP structure is then proposed by using BP neural network, furthermore, the optimal weights of action network and critic network are solved during the iteration process of HDP. At last, the performance and the effectiveness of HDP optimization are demonstrated through a case study of a building energy consumption monitoring system from practical engineering viewpoint. |
