جستجوی مقالات مرتبط با کلیدواژه « evolutionary algorithm » در نشریات گروه « برق »

Recommender systems are a subset of intelligent information filtering systems that discovers user interests and provide user-friendly recommendations. User-based collaborative filtering recommender systems is one of the most important types of recommender systems. However, they are faced with voluminous data and sparsity problems that have negative effects on the performance of the systems. In the proposed method, fuzzy C-ordered means clustering algorithm is integrated with a chaotic self-adaptive particle swarm evolutionary algorithm for clustering users. The proposed method aims to improve the rating prediction in large sparse datasets and reduce the negative impact of outliers and noisy data. Experiments have been conducted on real-world datasets to evaluate and prove the efficiency of the proposed method. Experimental results show the superiority of the proposed method that the state-of-the-art methods based on prediction error criteria, accuracy rates, and the computational time.

They are directly integrated into smart distribution networks and can supply stored energy during peak demand periods, while absorbing and storing energy during periods of low demand. This capability helps maintain a balance between supply and demand in power grids, preventing voltage fluctuations and the inability to meet peak loads during high-demand hours. Thanks to technological advancements, it is now possible to upgrade large-scale energy storage facilities. The modern architecture and technology of these facilities facilitate the efficient utilization of renewable energy sources, significantly reducing energy costs and increasing energy efficiency. Additionally, through the use of artificial intelligence algorithms and optimization techniques, the performance and operations of large-scale energy storage facilities can be enhanced. This article focuses on the management of large-scale energy storage facilities, introducing innovative measures that include constraints on the number of charge and discharge processes. Furthermore, the use of the advanced Fakete search algorithm is employed as a powerful and efficient method for solving the proposed model. This algorithm has the capability to find global optimal solutions and can significantly improve the efficiency and profitability of large-scale energy storage facilities. Simulation results demonstrate that adopting this approach in managing large-scale energy storage facilities leads to significant economic impacts. These impacts include reduced energy costs, increased efficiency, greater independence from fossil fuel resources, the preservation of grid stability, and improved performance of the power transmission system.

Edge computing is a computing paradigm that extends cloud services to devices at the edge. This processing model refers to technologies that allow computing and storage to be performed on devices at the edge of the network. In this architecture, computing and storage operations take place close to objects and data sources. In order to reduce latency and network traffic between end devices and cloud centers, groups at the edge have processing capabilities, perform a large number of processing and computing tasks, including data processing, temporary storage, device management, decision making, and privacy protection. Since the number of edge devices is large, there must be a mechanism to select these tasks and offload them to the cloud. The problem to be decided is that which one of the available edge devices should be selected for unloading and then unloaded. This problem is classified as one of the hard non-polynomial problems and by using deterministic algorithms simply and in polynomial time, it is not possible to find a suitable and efficient solution for it found.

In the optimization problems of intelligent distribution systems where there are many variables and parameters, providing an efficient algorithm that has the ability to converge and solve in large networks is one of the main challenges of researchers. In this paper, a compound integer quadratic optimization model for improving the performance of large-scale distribution network using demand-side management problem, energy storage system, battery-to-metro system, optimal control of OLTC and SVR tap-trans and distributed generation resources. Fossil and renewable are offered alongside capacitor and shunt reactors. The considered multi-objective function is a scenario-based stochastic model, which accurately models the uncertainties in renewable energy sources. According to the considered problems and also the model of large networks of 118 and 874 buses, most of the algorithms are not able to converge due to the existence of many variables. In this article, the optimal performance of the proposed hybrid evolutionary algorithm is shown on large distribution networks, which is able to reach global optimal solutions compared to similar algorithms.

With the increasing penetration of renewable energy sources such as wind and photovoltaic generation in future microgrids, challenges arise due to variable weather conditions. In this paper, a model is proposed to optimize the performance of microgrids under the worst-case scenario of renewable energy source failures using a bi-level optimization. In the upper-level problem, optimization is carried out in terms of energy loss reduction, load shedding in the load management program, as well as optimal charging and discharging of energy storage systems. The lower-level problem considers maximizing the utilization of renewable energy. A bi-level optimization solution method is proposed, which involves binary variables at both levels and is solved using a non-dominated sorting genetic algorithm (NSGA-II). The proposed model and algorithm are implemented using the Julia programming language. The performance of the model is examined under various conditions using a 33-bus microgrid, and the optimization results demonstrate the optimal performance of the microgrid under the worst-case scenario of renewable energy source failures.

Data clustering is one of the main steps in data mining, which is responsible for exploring hidden patterns in non-tagged data. Due to the complexity of the problem and the weakness of the basic clustering methods, most studies today are guided by clustering ensemble methods. Diversity in primary results is one of the most important factors that can affect the quality of the final results. Also, the quality of the initial results is another factor that affects the quality of the results of the ensemble. Both factors have been considered in recent research on ensemble clustering. Here, a new framework for improving the efficiency of clustering has been proposed, which is based on the use of a subset of primary clusters, and the proposed method answers the above questions and ambiguities. The selection of this subset plays a vital role in the efficiency of the assembly. Since evolutionary intelligent algorithms have been able to solve the majority of complex engineering problems, this paper also uses these intelligent methods to select subsets of primary clusters. This selection is done using three intelligent methods (genetic algorithm, simulation annealing and particle swarm optimization). In this paper a clustering ensemble method is proposed which is based on a subset of primary clusters. The main idea behind this method is using more stable clusters in the ensemble. The stability is applied as a goodness measure of the clusters. The clusters which satisfy a threshold of this measure are selected to participate in the ensemble. For combining the chosen clusters, a co-association based consensus function is applied. A new EAC based method which is called Extended Evidence Accumulation Clustering, EEAC, is proposed for constructing the Co-association Matrix from the subset of clusters. Experimental results on several standard datasets with normalized mutual information evaluation, Fisher and accuracy criteria compared to Alizadeh, Azimi, Berikov, CLWGC, RCESCC, KME, CFSFDP, DBSCAB, NSC and Chen methods show the significant improvement of the proposed method in comparison with other ones.

This paper presents a model for distribution network optimization considering a high penetration of photovoltaic (PV) sources and electric vehicle charging stations (EVCSs) based on on-load tap changing transformers (OLTC) and step voltage regulator (SVR), shunt capacitor (SC), and shunt reactor (ShR). The purpose is to prevent overvoltage due to power injection by PV sources and voltage drop due to EV charging in distribution networks. The proposed model is solved using a new hybrid algorithm called PSO-GA. Relevant studies show that with the increasing number of PSO replications, particle population variability is easily eliminated and placed in local optimization. The idea of ​​combining GA is based on the PSO introduced in this study. Crossover and mutations of GA are performed on the PSO population, which is useful for improving the overall optimal ability of particles and causing the algorithm to deviate from the local optimal point. Two different IEEE standard test networks are tested under different load scenarios to analyze the proposed model. The results reveal the performance of the proposed model.

Long-term prediction of time series is an important but challenging issue. Today, deep networks, especially Long short Term Memory (LSTM) networks, have been successfully used to predict time series. The LSTM network is capable of maintaining long-term dependencies, but its ability to assign varying degrees of attention to sub window features over multiple time steps is not sufficient. Also, the performance of these networks depends heavily on their hyper-parameters ​​and it is important to adopt an efficient method to ensure optimum values. In this study, to overcome the above challenges, an evolutionary attention-based deep LSTM for predicting multivariate time series is recommended that automatically finds one of the best combinations of LSTM parameter values and sub window features. The proposed algorithm uses a genetic algorithm to properly adjust the deep LSTM network architecture. In order to evaluate the performance of the proposed algorithm, three data sets in the fields of energy and environment have been used. The experimental results show that the proposed algorithm performs better than other basic models.

In power systems, reconfiguration is one of the simplest and most low-cost methods to reach many goals such as self-healing, reliability improvement, and power loss reduction, without including any additional components. Regarding the expansion of distribution networks, communications become more complicate and the number of parameters increases, which makes the reconfiguration problem infeasible using mathematical models. Therefore, using intelligent algorithms become candidate solutions. On the other hand, analysis of opened and closed switches should be without error and should be done in line with the network constraints like, tolerable current flow of each branch, permissible voltage of the busbars, and the line power flow. Therefore, among evolutionary algorithms, an algorithm with enough accuracy and convergence speed is used. In this study, the performance of binary bat, dragonfly, genetic, and PSO (Particle Swarm Optimization) algorithms is compared in the network reconfiguration IEEE 16-bus and 33-bus test systems with the aim of reaching a topology with the minimum loss in power and the maximum reliability. The results show that binary bat algorithm has the best performance among other algorithms.

Software defects detection is one of the most important challenges of software development and it is the most prohibitive process in software development. The early detection of fault-prone modules helps software project managers to allocate the limited cost, time, and effort of developers for testing the defect-prone modules more intensively.  In this paper, according to the importance of software defects detection, a method based on fuzzy sets and evolutionary algorithms is proposed. Due to the imbalanced nature of software defect detection datasets, benefits of fuzzy clustering algorithms were used to data sampling and more attention to the minority class. This method is a combined algorithm which, firstly has used fuzzy c-mean clustering as weighted bootstrap sampling. Weight of data (their membership’s degrees) increases for minority class. In the next step, the subtractive clustering algorithm is applied to produce the classifier which was trained by produced data in the previous step. The binary genetic algorithm was utilized to select appropriate features. The results and also comparisons with eight popular methods in software defect detection literature, show an acceptable performance of the proposed method. The experiments were performed on ten real-world datasets with a wide range of data sizes and imbalance rates. Also T-test is used as the statistical significance test for pair wise comparison of our proposed method against the others. The final results of T-test are shown in tables for three performance measures (G-mean, AUC and Balanced) over various datasets. (As the obtained results apparently show our proposed method has the ability to improve three aforementioned performance criteria simultaneously). Some methods just have improved the G-mean measure while the AUC and Balance criteria have lower values than the others. Securing a high level of three performance measures simultaneously illustrates the ability of our proposed algorithm for handling the imbalance problem of software defects detection datasets.

The increasing of population, energy demand and environmental pollution due to using fossil fuels, have guided the societies to utilize renewable energies. In this case, the solar chimney power plant is one of the most applied means for energy exploitation. Due to its low efficiency, optimization is a way for enhancing the system performance. In this study, optimization of solar chimney was carried out for the purpose of reaching the highest theoretical power. The objective function is the power output of the system and the solution is based on the optimum construction cost of a 200 MW power plant. The design variables cover the geometric parts including chimney height, chimney radius, collector height, collector radius and the turbine distance from the ground. Also, the mathematical model was validated with the experimental data of the Manzanares solar chimney in Spain. For writing the optimization algorithm, the SQP (Sequential Quadratic Programming) algorithm and the evolutionary algorithm were utilized. Finally the optimum amounts for reaching the maximum power output were obtained.

In this paper to set the parameters of FACTS devices, genetics and particle swarm optimization with fuzzy logic techniques have been used. To optimize the reactive power consumption and reduce the line congestion, two types of FACTS devices; thyristor controlled series compensator (TCSC) and static var compensator (SVC), are used. Optimal location of FACTS devices on the network, which is under heavy loads, results to reduce the power losses, reactive power control and thus reduces the operating costs of the power system. In this paper, the fuzzy membership functions are used in order to determine the weak network buses in order to install the SVC. The values of reactive power through the lines are leads to locate the line which the TCSC should be installed. The method presented in this paper have been compared with other methods (e.g. analysis of eigenvalues) for optimal location of FACTS devices. The results of the simulations presented in this paper, proves the efficiency of the proposed method.