摘要
针对蝠鲼觅食优化（Manta Ray Foraging Optimization, MRFO）算法在求解高维复杂离散家庭能源调度问题时，存在种群多样性缺失、易陷入局部最优及多目标优化不平衡等问题，本研究提出一种离散长时记忆蝠鲼觅食优化（Discrete Long-term Memory Manta Ray Foraging Optimization, DLMMRFO）算法，该算法在MRFO框架中系统融合了五种改进策略，离散位置更新策略将连续搜索空间映射为可行调度方案，解决原始算法在处理离散变量时的失配问题；动态权重机制在迭代过程中自适应调整成本与峰均比（Peak-to-Average Ratio, PAR）的优化权重，平衡多目标优化进程；长时记忆机制通过保留历史优质解增强全局探索能力，防止早熟收敛；变异操作引入随机扰动以维持种群多样性；PAR专项优化策略则在迭代后期针对性地降低负荷峰均比。仿真实验通过增加家电数量来增加复杂度，设置简单与复杂两类场景，结果表明，相较于MRFO算法和未调度场景，DLMMRFO算法在简单场景中使成本降低7.89%和45.30%，PAR降低9.55%和33.91%；在复杂场景中，成本降幅达5.89%和53.29%，PAR降幅为16.82%和43.67%。为家庭能源管理提供了有效解决方案，有助于实现能源资源的高效配置与利用。
关键词： 家庭能源管理；蝠鲼觅食优化；需求响应；离散优化；峰值平均比
Abstract
To address the issues of population diversity loss, susceptibility to local optima, and unbalanced multi-objective optimization when the Manta Ray Foraging Optimization (MRFO) algorithm is applied to high-dimensional complex discrete home energy scheduling problems, this study proposes a Discrete Long-term Memory Manta Ray Foraging Optimization (DLMMRFO) algorithm. The DLMMRFO systematically integrates five improvement strategies within the MRFO framework: a discrete position update strategy maps the continuous search space to feasible scheduling solutions, resolving the mismatch problem of the original algorithm in handling discrete variables; a dynamic weight mechanism adaptively adjusts the optimization weights of cost and PAR during iteration to balance the multi-objective optimization process; a long-term memory mechanism enhances global exploration capability by preserving high-quality historical solutions, thereby preventing premature convergence; mutation operations introduce random perturbations to maintain population diversity; and a dedicated PAR optimization strategy specifically targets the reduction of the Peak-to-Average Ratio in the later stages of iteration. Simulation experiments, designed with both simple and complex scenarios by increasing the number of household appliances, demonstrate that compared to the original MRFO algorithm and an unscheduled scenario, the DLMMRFO algorithm reduces the cost by 7.89% and 45.30%, and the PAR by 9.55% and 33.91%, respectively, in the simple scenario. In the complex scenario, it achieves cost reductions of 5.89% and 53.29%, and PAR reductions of 16.82% and 43.67%, respectively. The proposed algorithm provides an effective solution for home energy management, contributing to the efficient allocation and utilization of energy resources.
Key words： Home energy management; Manta ray foraging optimization; Demand response; Discrete optimization; Peak-to-Average Ratio (PAR)
参考文献 References
[1] 付建勇, 智能电网中分布式能源接入对系统稳定性的影响研究[J]. 电气工程与自动化, 2024, 3: (2) : 31-34.
[2] 代业明,孙锡连,李陆,等.基于多层博弈的智能电网住宅电力实时需求响应机制[J].运筹与管理,2021,30(10):11-17.
[3] de Lima T D, Faria P, Vale Z. Optimizing home energy management systems: A mixed integer linear programming model considering battery cycle degradation[J]. Energy and Buildings, 2025, 329: 115251.
[4] Abreu C, Soares I, Oliveira L, et al. Application of genetic algorithms and the cross‐entropy method in practical home energy management systems[J]. IET Renewable Power Generation, 2019, 13(9): 1474-1483.
[5] 华聪聪, 冯胜, 李大华, 等. 基于改进量子遗传算法的光伏智能楼宇负荷优化[J]. 计算机应用与软件, 2024, 41(9): 77-82,105.
[6] 丁迅, 张忠, 夏兆俊, 等. 基于非侵入式负荷监测的家庭智慧用能管理研究[J]. 现代电力, 2022, 39(4): 496-504.
[7] Sivaranjani R, Rao P M. Smart energy optimization using new genetic algorithms in Smart Grids with the integration of renewable energy sources[M]//Sustainable Networks in Smart Grid. Academic Press, 2022: 121-147.
[8] 江泽昌, 刘天羽, 江秀臣, 等. 智能电网下多时间尺度家庭能量管理优化策略[J]. 太阳能学报, 2021, 42(1): 460-469.
[9] Abedin Z U, Shahid U, Mahmood A, et al. Application of PSO for HEMS and ED in Smart Grid[C]//2015 Ninth International Conference on Complex, Intelligent, and Software Intensive Systems. IEEE, 2015: 260-266.
[10] Khalid A, Javaid N, Guizani M, et al. Towards dynamic coordination among home appliances using multi-objective energy optimization for demand side management in smart buildings[J]. IEEE access, 2018, 6: 19509-19529.
[11] Zhao W, Zhang Z, Wang L. Manta ray foraging optimization: An effective bio-inspired optimizer for engineering applications[J]. Engineering Applications of Artificial Intelligence, 2020, 87: 103300.
[12] Houssein E H, Emam M M, Ali A A. Improved manta ray foraging optimization for multi-level thresholding using COVID-19 CT images[J]. Neural Computing and Applications, 2021, 33(24): 16899-16919.
[13] 陈晨, 郝国凯, 陈高伟, 等. 人类偏好强化学习与演化计算融合的家庭能源系统需求响应优化[J/OL]. 上海交通大学学报, 2025: 1-22 [2025-09-25].
[14] Economics F, First S. Demand side response in the domestic sector—a literature review of major trials[R]. London: Final Report, 2012.
[15] Aslam S, Javaid N, Khan F A, et al. Towards efficient energy management and power trading in a residential area via integrating a grid-connected microgrid[J]. Sustainability, 2018, 10(4): 1245.
[16] Youssef H, Kamel S, Hassan M H. Smart home energy management and power trading optimization using an enhanced manta ray foraging optimization[J]. Scientific Reports, 2023, 13(1): 22163.