The revolution represented by third-generation photovoltaic devices relied on the discovery of various hybrid organic-inorganic perovskite materials to convert solar into electrical energy. One of the advantages of su...
详细信息
The revolution represented by third-generation photovoltaic devices relied on the discovery of various hybrid organic-inorganic perovskite materials to convert solar into electrical energy. One of the advantages of such cells is their low cost due to the raw materials and cheap production methods used. Nevertheless, these cells face several challenges, such as inadequate stability and the hysteresis phenomenon. To overcome these, perovskite solar cell (PSCs) with planar and inverted structures have been utilized with an inorganic hole transport layer (HTL), achieving acceptable efficiency. As there is no closed-form system of equations to describe the operation of such cells, neural networks have been employed for their modeling. In optimizationalgorithms, the values of the parameters must be swept, since most current simulation tools cannot use them directly. Such software optimization can notably decrease the cost of cell design. This paper presents a practical way to achieve the mentioned aim. In particular, an artificial neural network (ANN) is exploited for the modeling, then an evolutionaryparticleswarmoptimization (E-PSO) algorithm is developed to optimize the structure to achieve the highest efficiency based on searching the energy conversion. The results of the simulations are then employed in SCAPS software to train the neural network. This optimization leads to the achievement of an efficiency of 23.76% for the proposed structure, better than values reported in literature.
The non-oriented two-dimensional bin packing problem is dealing with a set of rectangular pieces that need to be packed into identical rectangular bins. Moreover and in order to minimize the number of bins, the pieces...
详细信息
ISBN:
(纸本)9781457707391
The non-oriented two-dimensional bin packing problem is dealing with a set of rectangular pieces that need to be packed into identical rectangular bins. Moreover and in order to minimize the number of bins, the pieces are allowed to rotate by 90 degrees without overlapping. There are many real life applications for this operations research problem. Among these applications: loading of boxes to pallets, trucks and containers, packing of box bases on shelves and other applications in the wood and metal industry. In this paper, we propose evolutionary particle swarm optimization algorithm (EPSO) for solving the non-oriented two-dimensional bin packing problem. Extensive numerical investigations are performed to determine the solution quality of the proposed algorithm. Moreover, the performance of our proposed algorithm is compared with a best known greedy algorithm published in the literature.
Various optimization methods are used along with the standard clustering algorithms to make the clustering process simpler and quicker. In this paper we propose a new hybrid technique of clustering known as K-Evolutio...
详细信息
ISBN:
(纸本)9781450300643
Various optimization methods are used along with the standard clustering algorithms to make the clustering process simpler and quicker. In this paper we propose a new hybrid technique of clustering known as K-evolutionaryparticleswarmoptimization (KEPSO) based on the concept of particleswarmoptimization (PSO). The proposed algorithm uses the K-means algorithm as the first step and the evolutionaryparticleswarmoptimization (EPSO) algorithm as the second step to perform clustering. The experiments were performed using the clustering benchmark data. This method was compared with the standard K-means and EPSO algorithms. The results show that this method produced compact results and performed faster than other clustering algorithms. Later, the algorithm was used to cluster web pages. The web pages were clustered by first cleaning the unnecessary data and then labeling the obtained web pages to categorize them.
暂无评论