A custom designed and well monitored substation communication network (SCN) can maintain the fast and reliable information transmission and lead to improved operation and management of a substation automation system (SAS). In order to achieve this goal, a traffic flow model, including a port connection model, a traffic flow source model and a traffic flow service model of a SCN is developed in this paper. Based on the traffic flow model, a traffic flow calculation algorithm is designed to obtain the distribution of traffic load and maximum message delay. In order to verify the accuracy of the proposed method, the SCN of a simplified substation is established in the laboratory. And the distribution of traffic load and maximum message delay calculated using the proposed method is compared to that measured by a network analyzer. Further more, possible applications, such as network device selection, network performance analysis and sensitivity analysis, of the proposed method are demonstrated based on a typical 220 kV substation.Index Terms-substation automation system (SAS), traffic flow analytical model, IEC 61850, traffic load distribution, maximum message delay distribution.

No abstract

No abstract

This paper develops a multi-timescale coordinated operation method for microgrids based on modern deep reinforcement learning. Considering the complementary characteristics of different storage devices, the proposed approach achieves multi-timescale coordination of battery and supercapacitor by introducing a hierarchical two-stage dispatch model. The first stage makes an initial decision irrespective of the uncertainties using the hourly predicted data to minimize the operational cost. For the second stage, it aims to generate corrective actions for the first-stage decisions to compensate for real-time renewable generation fluctuations. The first stage is formulated as a non-convex deterministic optimization problem, while the second stage is modeled as a Markov decision process solved by an entropy-regularized deep reinforcement learning method, i.e., the Soft Actor-Critic. The Soft Actor-Critic method can efficiently address the exploration–exploitation dilemma and suppress variations. This improves the robustness of decisions. Simulation results demonstrate that different types of energy storage devices can be used at two stages to achieve the multi-timescale coordinated operation. This proves the effectiveness of the proposed method.

No abstract