Scholarlink

<p>Traditional scheduling of integrated electricity and heating systems with high wind penetration often leads to significant wind power curtailment and increased operating costs. To address these challenges, this study proposes a novel hybrid framework that combines the Sculptor Optimization Algorithm (SOA) with the Quantum Kernel Self-Attention Network (QKSAN) within an energy hub model for district energy networks. The SOA is employed to optimize the operating schedules of heat generation units and thermal storage, while the QKSAN enhances the accuracy of heating load predictions. This dual capability improves flexibility, reduces curtailment, and ensures more reliable system operation. The proposed SOA-QKSAN is implemented and evaluated in MATLAB Simulink, and benchmarked against established methods, including the light spectrum optimizer (LSO), particle swarm optimization (PSO), and sand cat swarm optimization (SCSO). Results demonstrate that SOA-QKSAN reduces system loss to 0.5&#xa0;kW, representing an 86% improvement compared to SCSO and over 85% compared to LSO, while lowering operating cost to €67, a 31% reduction relative to LSO and 6% reduction relative to SCSO. Thus, the proposed SOA-QKSAN framework provides a practical decision-making tool for energy operators, enabling efficient integration of renewable generation while significantly reducing system loss and operating cost compared to conventional methods.</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

Integrating heat and electricity with an energy hub framework for load flow analysis in district energy networks using SOA-QKSAN technique

  • 期刊论文

  • 发表日期：

    2026年1月9日

查看全文
  • S. Sridharan,
  • Jayarama Pradeep,
  • P. Velmurugan,
  • V. Vasan Prabhu

摘要

Traditional scheduling of integrated electricity and heating systems with high wind penetration often leads to significant wind power curtailment and increased operating costs. To address these challenges, this study proposes a novel hybrid framework that combines the Sculptor Optimization Algorithm (SOA) with the Quantum Kernel Self-Attention Network (QKSAN) within an energy hub model for district energy networks. The SOA is employed to optimize the operating schedules of heat generation units and thermal storage, while the QKSAN enhances the accuracy of heating load predictions. This dual capability improves flexibility, reduces curtailment, and ensures more reliable system operation. The proposed SOA-QKSAN is implemented and evaluated in MATLAB Simulink, and benchmarked against established methods, including the light spectrum optimizer (LSO), particle swarm optimization (PSO), and sand cat swarm optimization (SCSO). Results demonstrate that SOA-QKSAN reduces system loss to 0.5 kW, representing an 86% improvement compared to SCSO and over 85% compared to LSO, while lowering operating cost to €67, a 31% reduction relative to LSO and 6% reduction relative to SCSO. Thus, the proposed SOA-QKSAN framework provides a practical decision-making tool for energy operators, enabling efficient integration of renewable generation while significantly reducing system loss and operating cost compared to conventional methods.