We present a new approach based on honey-bee mating optimization to estimate the state variables in distribution networks including distributed generators. The proposed method considers practical models of electrical ...We present a new approach based on honey-bee mating optimization to estimate the state variables in distribution networks including distributed generators. The proposed method considers practical models of electrical equipments such as static var compensators, voltage regulators, and under-load tap changer transformers, which have usually nonlinear and discrete characteristics. The feasibility of the proposed approach is demonstrated by comparison with the methods based on neural networks, ant colony optimization, and genetic algorithms for two test systems, a network with 34-bus radial test feeders and a realistic 80-bus 20 kV network.展开更多
This paper proposes an integration of recent metaheuristic algorithm namely Evolutionary Mating Algorithm (EMA) in optimizing the weights and biases of deep neural networks (DNN) for forecasting the solar power genera...This paper proposes an integration of recent metaheuristic algorithm namely Evolutionary Mating Algorithm (EMA) in optimizing the weights and biases of deep neural networks (DNN) for forecasting the solar power generation. The study employs a Feed Forward Neural Network (FFNN) to forecast AC power output using real solar power plant measurements spanning a 34-day period, recorded at 15-minute intervals. The intricate nonlinear relationship between solar irradiation, ambient temperature, and module temperature is captured for accurate prediction. Additionally, the paper conducts a comprehensive comparison with established algorithms, including Differential Evolution (DE-DNN), Barnacles Mating Optimizer (BMO-DNN), Particle Swarm Optimization (PSO-DNN), Harmony Search Algorithm (HSA-DNN), DNN with Adaptive Moment Estimation optimizer (ADAM) and Nonlinear AutoRegressive with eXogenous inputs (NARX). The experimental results distinctly highlight the exceptional performance of EMA-DNN by attaining the lowest Root Mean Squared Error (RMSE) during testing. This contribution not only advances solar power forecasting methodologies but also underscores the potential of merging metaheuristic algorithms with contemporary neural networks for improved accuracy and reliability.展开更多
文摘We present a new approach based on honey-bee mating optimization to estimate the state variables in distribution networks including distributed generators. The proposed method considers practical models of electrical equipments such as static var compensators, voltage regulators, and under-load tap changer transformers, which have usually nonlinear and discrete characteristics. The feasibility of the proposed approach is demonstrated by comparison with the methods based on neural networks, ant colony optimization, and genetic algorithms for two test systems, a network with 34-bus radial test feeders and a realistic 80-bus 20 kV network.
基金supported by the Ministry of Higher Education Malaysia(MOHE)under Fundamental Research Grant Scheme(FRGS/1/2022/ICT04/UMP/02/1)Universiti Malaysia Pahang Al-Sultan Abdullah(UMPSA)under Distinguished Research Grant(#RDU223003).
文摘This paper proposes an integration of recent metaheuristic algorithm namely Evolutionary Mating Algorithm (EMA) in optimizing the weights and biases of deep neural networks (DNN) for forecasting the solar power generation. The study employs a Feed Forward Neural Network (FFNN) to forecast AC power output using real solar power plant measurements spanning a 34-day period, recorded at 15-minute intervals. The intricate nonlinear relationship between solar irradiation, ambient temperature, and module temperature is captured for accurate prediction. Additionally, the paper conducts a comprehensive comparison with established algorithms, including Differential Evolution (DE-DNN), Barnacles Mating Optimizer (BMO-DNN), Particle Swarm Optimization (PSO-DNN), Harmony Search Algorithm (HSA-DNN), DNN with Adaptive Moment Estimation optimizer (ADAM) and Nonlinear AutoRegressive with eXogenous inputs (NARX). The experimental results distinctly highlight the exceptional performance of EMA-DNN by attaining the lowest Root Mean Squared Error (RMSE) during testing. This contribution not only advances solar power forecasting methodologies but also underscores the potential of merging metaheuristic algorithms with contemporary neural networks for improved accuracy and reliability.
文摘为解决森林冠层图像因结构复杂,提取时受光照不均的影响而导致分割精度低的问题,采用一种基于自适应调整策略的混沌藤壶交配优化算法(Chaotic Adaptive Barnacle Mating Optimization,CABMO)的森林冠层图像分割方法。首先采用Logistic混沌映射初始化藤壶种群以提高算法的探索能力;然后设计非线性递增阴茎系数使探索和开发之间更平衡;最后将Kapur熵作为适应度函数,利用CABMO算法选取适应度函数的最优值,降低复杂度的同时,加强阈值的搜索效率。为验证CABMO算法在森林冠层图像分割上的有效性,以适应度值、峰值信噪比值(Peak Signal to Noise Ratio,PSNR)、特征相似性指数测试值(feature similarity index mersure,FSIM)和计算时间作为性能指标来评估分割效果。研究结果表明,在适应度值、PSNR值和FSIM值上CABMO算法分别以100%、99%、97.9%的占比优于对比算法,在计算时间上100%优于基本藤壶交配优化算法(Barnacle Mating Optimization,BMO)。结果表明,CABMO算法在提高森林冠层图像分割精度的同时也获得了更高质量的分割图像。
文摘为平衡多目标演化算法求解不同优化问题以及求解同一优化问题时不同搜索阶段的勘探与开采能力,并考虑到减小聚类算法辅助演化算法时产生的计算开销,提出了一种基于自适应交配限制概率的自组织多目标演化算法(adaptive mating restriction probability based self-organizing multiobjective evolutionary algorithm,ASMEA).首先,ASMEA在每一代利用自组织映射(self-organizing map,SOM)算法建立了演化种群个体间的邻居关系,基于此关系有利于算子实施恰当的重组操作,并在演化算法后期产生优质解,与此同时,为了节省利用SOM建立当前种群个体之间的邻居关系时引起的计算开销,将SOM与演化算法相融合,交替地进行SOM训练与种群演化.然后,运用交配限制概率控制交配父代来源于SOM发现的邻居种群或者是整个种群,以分别加强开采和勘探.最后,根据采用不同父代来源的重组在过去一定代数产生后代个体的效用,自适应地调整算法的交配限制概率.利用ASMEA和5种具有代表性的多目标演化算法对标准测试题进行求解,求解结果表明:ASMEA在搜索质量、搜索效率以及可视化方面优于其他5种算法,从而验证了ASMEA算法对多目标优化问题具有良好的求解性能.
