Multi-park comprehensive energy scheduling method and system

Abstract

The embodiment of the invention provides a multi-park comprehensive energy scheduling method and system, and the method comprises the steps: building a reinforcement learning agent for each park based on the new energy, energy storage, energy conversion equipment and multi-energy users of each park; inputting each reinforcement learning agent into the multi-agent depth deterministic strategy gradient model, and performing scheduling decision in a real physical space by adopting a decentralized execution method; and obtaining the multi-agent depth deterministic strategy gradient model by training in a virtual environment by adopting a centralized training method. According to the embodiment of the invention, the reinforcement learning agent of a single park is established, then based on the established multi-agent depth deterministic strategy gradient model, training is carried out in a virtual environment by adopting a centralized training method, scheduling decision making is carried out in a real physical space by adopting a decentralized execution method, the method does not depend on accurate prediction of uncertainties, the privacy of each park is protected, and the operation cost of each park is reduced.

Description

technical field [0001] The invention relates to the field of multi-park integrated energy, in particular to a multi-park integrated energy scheduling method and system. Background technique [0002] The collaborative optimization operation of multi-park integrated energy systems can make full use of the flexibility of multi-energy coupling, release the potential of distributed resources, further reduce operating costs, and at the same time reduce dependence on external energy networks. However, the problem of multi-subject benefit distribution, the need for privacy protection, and the existence of multiple uncertainties have brought great challenges to the coordinated operation of multi-parks. [0003] At present, the research on the collaborative optimization scheduling method of multi-park integrated energy system mainly includes two methods: centralized optimization and distributed optimization. For example, a multi-park comprehensive energy system optimization schedulin...

AI Technical Summary

Problems solved by technology

However, most of the above studies apply reinforcement learning to the scenario where the integrated energy system is modeled as a single agent, and there is still a lack of research on the application of reinforcement learning to the multi-stakeholder scenario of the integrated energy system

Images