Research On Smart Operation Methods For Building Multi-Energy Systems

The energy consumption and carbon emission generated by buildings account for a high proportion of the world’s total energy consumption and carbon emission.In 2019,the energy consumed by the world’s buildings accounted for about 30% of the world’s total energy,and the carbon emission generated accounted for about 28% of the world’s total carbon emission.At present,the global energy supply mainly relies on non-renewable energy sources such as fossil fuels,which leads to increasingly energy depletion and environmental problems.In recent years,hydrogen energy has received widespread attention due to its clean,renewable,wide-ranging sources,convenient storage and transportation,high utilization rate,and has been recognized as a promising alternative to fossil fuels.In addition,the coordinated operation of hydrogen energy storage system and other energy storage systems(e.g.,thermal energy storage system and electrical energy storage system)contributes to the improvement of building energy efficiency and the reduction of system costs.Therefore,it is very necessary to study the optimal operation method of a hydrogen-included building multi-energy system.In view of the above-mentioned system optimal operation problem,existing researches have proposed several methods.However,they did not consider building thermal dynamics,which means that the high thermal inertia of the building can not be exploited to reduce operational cost in the premise of maintaining a comfortable temperature range.For this reason,this thesis studies the optimal operation of a hydrogen-included building multi-energy system in the case of considering the building thermal dynamics.Specifically,we first formulate an operational cost minimization problem for a hydrogen-included building multi-energy system with the consideration of hydrogen-electric-thermal hybrid energy storage and controllable thermal loads.Due to the existence of many uncertain system parameters,temporally and spatially coupled operation constraints,unknown explicit building thermal dynamics model and the coupling between electrical energy flow and thermal energy flow,it is very challenging to solve the formulated problem.In order to address the above challenges,we reformulate the optimization problem as a markov decision process,and propose an energy optimization algorithm based on the combination of deep deterministic policy gradient and priority experience replay.The proposed algorithm does not require any prior knowledge of uncertain parameters and explicit building thermal dynamics model.Extensive simulation results based on real-world traces show the effectiveness and robustness of the proposed algorithm.Compared with other schemes,the proposed algorithm can reduce operating costs by 5.12%-24.86% while maintaining a comfortable temperature range.Finally,we make a summary of this thesis and look forward to the next research work.