Journal
JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY
Volume 11, Issue 1, Pages 107-119Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.35833/MPCE.2022.000271
Keywords
Switches; Optimization; Real-time systems; Mathematical models; Distribution networks; Costs; Reinforcement learning; Data-driven; distribution network reconfiguration; deep reinforcement learning; distributed generation
Categories
Ask authors/readers for more resources
This paper proposes a real-time reconfiguration method for the integration of distributed generation and distribution network using deep reinforcement learning. By constructing a Markov decision process-based reconfiguration model and a soft open point optimization model, the decision-making can be achieved in milliseconds. The proposed method effectively reduces the operation cost and solves the overvoltage problem caused by high photovoltaic integration.
With the large-scale distributed generations (DGs) being connected to distribution network (DN), the traditional day-ahead reconfiguration methods based on physical models are challenged to maintain the robustness and avoid voltage off-limits. To address these problems, this paper develops a deep reinforcement learning method for the sequential reconfiguration with soft open points (SOPs) based on real-time data. A state-based decision model is first proposed by constructing a Marko decision process-based reconfiguration and SOP joint optimization model so that the decisions can be achieved in milliseconds. Then, a deep reinforcement learning joint framework including branching double deep Q network (BDDQN) and multi-policy soft actor-critic (MPSAC) is proposed, which has significantly improved the learning efficiency of the decision model in multi-dimensional mixed-integer action space. And the influence of DG and load uncertainty on control results has been minimized by using the real-time status of the DN to make control decisions. The numerical simulations on the IEEE 34-bus and 123-bus systems demonstrate that the proposed method can effectively reduce the operation cost and solve the overvoltage problem caused by high ratio of photovoltaic (PV) integration.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available