Structure learning is the core of graph model Bayesian Network learning, and the current mainstream single search algorithm has problems such as poor learning effect, fuzzy initial network, and easy falling into local...
详细信息
Structure learning is the core of graph model Bayesian Network learning, and the current mainstream single search algorithm has problems such as poor learning effect, fuzzy initial network, and easy falling into local optimum. In this paper, we propose a heuristic learning algorithmhc-PSO combining the hc (Hill Climbing) algorithm and PSO (Particle Swarm Optimization) algorithm, which firstly uses hc algorithm to search for locally optimal network structures, takes these networks as the initial networks, then introduces mutation operator and crossover operator, and uses PSO algorithm for global search. Meanwhile, we use the DE (Differential Evolution) strategy to select the mutation operator and crossover operator. Finally, experiments are conducted in four different datasets to calculate BIC (Bayesian Information Criterion) and HD (Hamming Distance), and comparative analysis is made with other algorithms, the structure shows that the hc-PSO algorithm is superior in feasibility and accuracy.
This study deals with a new version of hill-climbing (hc) algorithm for maximum power peak estimation of the solar photovoltaic (PV) panel, which has self-estimation (SEn) and decision-taking ability. Moreover, it is ...
详细信息
This study deals with a new version of hill-climbing (hc) algorithm for maximum power peak estimation of the solar photovoltaic (PV) panel, which has self-estimation (SEn) and decision-taking ability. Moreover, it is based on a single sensor, which is applicable for the PV array-fed battery charging. The working principle of Self-Estimated hc (SEhc) algorithm is based on three consecutive operating points on the power-current characteristic. By using perpendicular line analogy (PLA), these points decide direction, and an optimised operating position for next iteration, which is responsible for quick maximum power point tracking as well as improved dynamic performance. Moreover, in every new iteration, the step size is reduced by 90% from the previous step size, which provides an oscillation-free steady-state performance. Owing to a single sensor, the computational burden, as well as calculation complexity of the SEhc algorithm is less, so it can be simply implemented on a cheaper microcontroller. The effectiveness of the proposed technique is validated by MATLAB simulation as well as tested on the experimental prototype. Moreover, the performance of SEhc algorithm is compared with recent state-of-the-art techniques. The highly suitable and satisfactory results of SEhc algorithm show the superiority over the state-of-the-art methods.
This study presents a single current sensor based hybrid maximum power point tracking method to track the global maximum power point (GMPP) of the photovoltaic (PV) array during the mismatch insolation conditions. Thi...
详细信息
This study presents a single current sensor based hybrid maximum power point tracking method to track the global maximum power point (GMPP) of the photovoltaic (PV) array during the mismatch insolation conditions. This method combines the artificial bee colony (ABC) and hill climbing (hc) algorithms to track the GMPP of a PV array. The proposed method uses the hc algorithm to identify the occurrence of mismatch insolation conditions on PV array. During the mismatch insolation conditions, the proposed method scans the battery charging current (I-charge) versus duty cycle (D) characteristics of the power electronic interface circuit to classify the type of shading pattern of P-V curve and also to identify the vicinity of the GMPP. Based on the kind of shading pattern of a P-V curve, the proposed method operates either ABC or hc algorithm to track the GMPP. To improve the convergence speed of the proposed method, the search space of the ABC algorithm is reduced. The proposed method is modelled and simulated in MATLAB software and its performance is validated experimentally for various mismatch insolation conditions.
暂无评论