系统仿真学报 ›› 2022, Vol. 34 ›› Issue (10): 2142-2151.doi: 10.16182/j.issn1004731x.joss.21-0534

• 仿真建模理论与方法 • 上一篇    下一篇

一种量子磷虾群融合算法及其应用

冯增喜1,2(), 赵锦彤1, 李诗妍1, 杨亚龙2(), 陈海越1, 张聪1   

  1. 1.西安建筑科技大学 建筑设备科学与工程学院, 陕西 西安 710055
    2.安徽建筑大学 智能建筑与建筑节能安徽省重点实验室, 安徽 合肥 230022
  • 收稿日期:2021-06-08 修回日期:2021-09-11 出版日期:2022-10-30 发布日期:2022-10-18
  • 通讯作者: 杨亚龙 E-mail:fengzengxi2000@163.com;yalong_yang2020@163.com
  • 作者简介:冯增喜(1979-),男,博士,副教授,研究方向为建筑节能、智能建筑、智慧城市。E-mail:fengzengxi2000@163.com
  • 基金资助:
    国家重点研发计划(2017YFC0704104-03);陕西省科技厅专项(2017JM6106);安徽建筑大学智能建筑与建筑节能安徽省重点实验室2018年度开放课题(IBES2018KF08)

A Quantum Krill Herd Fusion Algorithm and Its Application

Zengxi Feng1,2(), Jintong Zhao1, Shiyan Li1, Yalong Yang2(), Haiyue Chen1, Cong Zhang1   

  1. 1.School of Building Services Science and Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China
    2.Anhui Key Laboratory of Intelligent Building and Building Energy Conservation, Anhui Jianzhu University, Hefei 230022, China
  • Received:2021-06-08 Revised:2021-09-11 Online:2022-10-30 Published:2022-10-18
  • Contact: Yalong Yang E-mail:fengzengxi2000@163.com;yalong_yang2020@163.com

摘要:

针对磷虾群算法和量子进化算法的缺陷,提出了一种量子磷虾群融合算法(quantum krill herd fusion algorithm, QKH)该算法通过采用双链实数编码量子磷虾位置,加快收敛速度,避免量子观测的随机性和复杂性;通过利用动态调整的量子磷虾群旋转门更新磷虾位置,提升收敛精度,提高量子旋转相位的确定效率;通过改进的量子全干扰交叉策略,避免算法陷入局部最优,提升优化效率。通过经典测试函数验证了所提算法的优势。建立了QKH-BPNN空调负荷预测模型,仿真结果表明:该模型具有更好的准确性和稳定性。

关键词: 量子磷虾群融合算法, 双链实数编码, 量子磷虾群旋转相位, 改进的量子全干扰交叉, QKH-BPNN预测

Abstract:

Aiming at the defects of krill herd algorithm and quantum evolutionary algorithm, a quantum krill herd fusion algorithm (QKH) is proposed. The algorithm uses double-chain real numbers to encode the krill position, which can speed up the convergence speed, and avoids the randomness and complexity of quantum observations. The dynamically adjusted quantum krill herd rotation phase update strategy improves the convergence accuracy, and the efficiency of determining the quantum rotation phase. The introduction of an improved quantum full interference crossover strategy can prevent the fusion algorithm from falling into a local optimum, and can improve the optimization efficienal. The advantages of the quantum krill herd fusion optimization algorithm are verified by the classic test functions. A QKH-BPNN prediction model is established for air conditioning load forecasting, and the results show that the model has better accuracy and higher stability.

Key words: quantum krill herd fusion algorithm, double-chain real numbers encoding, quantum krill herd rotation phase, improved quantum full interference crossover, QKH-BPNN prediction

中图分类号: