Scholarlink

<p>In the new power system, intermittency and randomness of distributed renewable energy output, as well as the power fluctuation of user-side controllable load, pose significant challenges to the safe and stable operation of the power grid. Based on the information collected by internet of things (IoT) devices, the distribution regulation center can issue commands through the communication network to prompt user-side resources to participate in demand response, thereby ensuring the stable operation of the power grid. However, with the development of the digitalization process, the power grid and communication network present characteristics of deep coupling, where factors such as regulation command communication delay and packet loss severely affect the ability of user-side resources to participate in demand response, leading to high demand response regulation cost and poor robustness. To address these issues, this paper proposes a demand response autonomous decision-making method considering regulation command communication delay and reliability. Initially, we construct a cloud-edge-end collaborative demand response autonomous decision-making framework considering power grid-communication network coupling. Subsequently, considering the output of user-side resources and power grid constraints, we formulate the optimization problem with the objective of minimizing the weighted sum of aggregated regulation cost and distribution grid loss. Then, based on the information gap decision theory (IGDT), the uncertainties of the outputs of renewable energy resources such as distributed wind power and photovoltaic (PV) are measured, and a robust optimization model for autonomous decision-making based on risk aversion is established. Finally, we propose a deep actor-critic (DAC)-based communication delay reliability-aware optimization method for demand response autonomous decision-making, where the impact of communication delay and packet loss on user-side resources outputs are taken into account. This method constructs a multi-objective Markov decision process (MDP) model based on the regulation command communication delay and packet loss awareness, adjusts the power output range, and proposes the dual cooperative DAC algorithm to iteratively obtain the optimal decision and accelerate algorithm convergence. Simulation results demonstrate that the proposed algorithm can effectively reduce the regulation cost of user-side resources participating in demand response and grid loss, showing awesome economic efficiency and robustness.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Demand Response Autonomous Decision-Making Method Considering Regulation Command Communication Delay and Reliability

  • 期刊论文

  • 发表日期：

    2025年6月11日

查看全文
  • Long Wang,
  • Huishan Huang,
  • Hui Yu,
  • Yi Wang,
  • Tingzhe Pan,
  • Wangzhang Cao

摘要

In the new power system, intermittency and randomness of distributed renewable energy output, as well as the power fluctuation of user-side controllable load, pose significant challenges to the safe and stable operation of the power grid. Based on the information collected by internet of things (IoT) devices, the distribution regulation center can issue commands through the communication network to prompt user-side resources to participate in demand response, thereby ensuring the stable operation of the power grid. However, with the development of the digitalization process, the power grid and communication network present characteristics of deep coupling, where factors such as regulation command communication delay and packet loss severely affect the ability of user-side resources to participate in demand response, leading to high demand response regulation cost and poor robustness. To address these issues, this paper proposes a demand response autonomous decision-making method considering regulation command communication delay and reliability. Initially, we construct a cloud-edge-end collaborative demand response autonomous decision-making framework considering power grid-communication network coupling. Subsequently, considering the output of user-side resources and power grid constraints, we formulate the optimization problem with the objective of minimizing the weighted sum of aggregated regulation cost and distribution grid loss. Then, based on the information gap decision theory (IGDT), the uncertainties of the outputs of renewable energy resources such as distributed wind power and photovoltaic (PV) are measured, and a robust optimization model for autonomous decision-making based on risk aversion is established. Finally, we propose a deep actor-critic (DAC)-based communication delay reliability-aware optimization method for demand response autonomous decision-making, where the impact of communication delay and packet loss on user-side resources outputs are taken into account. This method constructs a multi-objective Markov decision process (MDP) model based on the regulation command communication delay and packet loss awareness, adjusts the power output range, and proposes the dual cooperative DAC algorithm to iteratively obtain the optimal decision and accelerate algorithm convergence. Simulation results demonstrate that the proposed algorithm can effectively reduce the regulation cost of user-side resources participating in demand response and grid loss, showing awesome economic efficiency and robustness.