جستجوی مقالات مرتبط با کلیدواژه "performance improvement" در نشریات گروه "برق"

This paper aims to study the appropriate data mining method to extract the rules from a data set and examining the benefits of using the cuckoo algorithm to extract association rules and compare the execution time of the cuckoo algorithm and genetic algorithm (GA). Therefore, an algorithm is proposed that includes two parts: preprocessing and mining. The first part presents the procedures related to the calculation of cuckoo fit values and in the second part of the algorithm, which is the main achievement of this research. Support and confidence The best position can show the least confidence and support.These mining results can be used to continue mining the association rules. The proposed algorithm is based on the cuckoo search. It hides the sensitive relationship rules with a lower time cost and, at the same time, controls the peripheral effects of non-sensitive rules in a better way. This aim is achieved using recurring to the objective function. The GA is set to be the evaluation criterion to show the prominence of the proposed method. In this method, we compare the speed of the cuckoo algorithm with the genetic algorithm, which uses genetic evolution as a problem-solving model. In general, it is an algorithm based on repetition, most of its parts are selected as random processes, and these algorithms are part of the fitting function. It was chosen as a criterion and we paid .It is scientifically proven that the cuckoo algorithm outperforms the GA in the execution time.

The purpose using capacitors in distribution networks is to reduce the total losses of the network. Capacitors help regulate the power factor and voltage in the electrical distribution system, and can be controlled remotely, in and out of the system. Capacitor placement depends on the objective function, which is usually single objective or multi objective. In this paper, the amount of capacitor at minimum load is determined using a genetic algorithm. The calculation is done at peak load to determine the sensitivity of power losses. By using this method, the increase of the voltage caused by the lead phase of the system is prevented in the minimum load. A multi-purpose objective function to simultaneously reduce losses and improve the voltage profile of the optimal capacitor size in each section is detected by a genetic algorithm. To show the efficiency of the method, the capacitor placement results are compared using DIGSIENT software.

The use of artificial neural network in conjunction with artificial bee colony algorithm is proposed as a method for performance and emissions optimization of an SI engine. The case study here involves the oxygen enriched combustion of an SI engine fueled with hydrous ethanol and gasoline. In this study, the engine is considered as a black box and its performance and emissions were extracted experimentally at different intake air oxygen concentrations, hydrous ethanol injection rates, and ethanol concentration in the hydrous ethanol mixture. Then the simultaneous injection of hydrous ethanol and oxygen enriched combustion was investigated to maximize the fuel conversion efficiency and minimize the CO and NOx emissions. Therefore, an objective function consisting of both the emission and performance parameters was optimized using the Artificial Bee Colony algorithm. The engine model used in this optimization process was obtained from an Artificial Neural Network trained with experimental engine data. For operating speed of 3000 rpm, the optimization results indicated 1.21% improvement in fuel conversion efficiency and 31.11% and 13.94% reduction in CO and NOx emissions, respectively. At the speed of 2000 rpm, fuel conversion efficiency improved by 4.11% and CO emission decreased 18.73%, while NOx concentration increased 28.35%.

Smart Grid (SG) is an intelligent managed network inclusive various data networks. Due to using the two-way data and electricity flows in SG, relations among the network elements are in an efficient way. Path finding optimization is one of the important challenges in SG. In this paper, we propose a routing protocol, namely Neuro-Fuzzy Stable Optimization Multi-Constrained Routing (NFSOMCR), to investigate the optimal path between two nodes in the SG. For this purpose, seven parameters and one cost function are used to meet the important QoS requirements of SG. Depending on the different initializations applied on the parameters, some routes with their constraints are found out by Dijkstra routing algorithm that form the inputs of the Neuro-Fuzzy system. The output of this system is the optimized cost function as well as the optimal paths between two nodes. Experimental results show that the proposed method outperforms existing works in terms of power cost and throughput.