Scholarlink

<p>Against the backdrop of global energy structure transformation, the intelligent scheduling of residential energy systems has emerged as a pivotal technology for enhancing energy utilization efficiency and reducing electricity costs. With the large-scale integration of renewable energy and the deepening reform of electricity marketization, RTP mechanisms are being progressively implemented in developed countries, creating new opportunities for demand-side response. Addressing the core contradiction of the current collaborative research on RTP and household energy scheduling, which faces a triple disconnection of “algorithm-mechanism-user”, this study considers the synergistic potential among electricity consumption behavior, supply and storage equipment, and electricity pricing mechanism in the household energy system. With the real-time electricity pricing mechanism as the core driver, intelligent scheduling models based on CPLEX, PSO, and DDPG are established respectively. Based on measured data, the scheduling strategies of different algorithms are simulated under seasonal typical day and typical month scenarios, and the electricity costs are compared. Furthermore, the performance of different algorithms in photovoltaic power generation, energy storage scheduling, and electricity trading is evaluated based on the simulation results, providing suggestions for matching algorithm selection strategies in different household energy consumption scenarios. The research results show that the CPLEX algorithm exhibits significant advantages in the long-term scheduling of the household energy system, reducing electricity costs by up to 54% compared to PSO and DDPG in the high-fluctuation market environment of winter. The findings of this study provide key technical references for constructing intelligent scheduling algorithms that couple dynamic electricity pricing mechanisms with complex energy consumption scenarios, and facilitate the transformation of household energy systems from “passive consumption” to “active profitability”.</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

Foresighted multi-algorithm energy scheduling management strategy for smart homes under dynamic electricity pricing

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月26日

查看全文
  • Xueyuan Zhao,
  • Xiaoyu Ying,
  • Fanyue Qian,
  • Tianyang Zhang,
  • Wanli Yin

摘要

Against the backdrop of global energy structure transformation, the intelligent scheduling of residential energy systems has emerged as a pivotal technology for enhancing energy utilization efficiency and reducing electricity costs. With the large-scale integration of renewable energy and the deepening reform of electricity marketization, RTP mechanisms are being progressively implemented in developed countries, creating new opportunities for demand-side response. Addressing the core contradiction of the current collaborative research on RTP and household energy scheduling, which faces a triple disconnection of “algorithm-mechanism-user”, this study considers the synergistic potential among electricity consumption behavior, supply and storage equipment, and electricity pricing mechanism in the household energy system. With the real-time electricity pricing mechanism as the core driver, intelligent scheduling models based on CPLEX, PSO, and DDPG are established respectively. Based on measured data, the scheduling strategies of different algorithms are simulated under seasonal typical day and typical month scenarios, and the electricity costs are compared. Furthermore, the performance of different algorithms in photovoltaic power generation, energy storage scheduling, and electricity trading is evaluated based on the simulation results, providing suggestions for matching algorithm selection strategies in different household energy consumption scenarios. The research results show that the CPLEX algorithm exhibits significant advantages in the long-term scheduling of the household energy system, reducing electricity costs by up to 54% compared to PSO and DDPG in the high-fluctuation market environment of winter. The findings of this study provide key technical references for constructing intelligent scheduling algorithms that couple dynamic electricity pricing mechanisms with complex energy consumption scenarios, and facilitate the transformation of household energy systems from “passive consumption” to “active profitability”.