Communications Internationales

Permanent URI for this collectionhttps://dspace.univ-boumerdes.dz/handle/123456789/11

Browse

Author: search.filters.author.Bendjeghaba, Omar

Search Results

Now showing 1 - 7 of 7
  • No Thumbnail Available
    Item
    A Practical Integrated Fault Location Technique for Radial Power Distribution Systems
    (IEEE, 2019) Hamadouche, Tarek; Bendjeghaba, Omar; Ahriche, Aimed
    power distribution systems (PDS) are becoming more complex and dispersed at long distances and different locations. With its radial and several laterals configuration, loads could be connected at similar distances from the substation which leads to a multi estimation of fault location and consuming more time for iterative fault location algorithms. In order to overcome those difficulties, a practical integrated fault location method for radial PDS is presented in this paper. The basic idea of the proposed approach is to partition a multi lateral distribution system to possible mono lateral system (MLSs) by a proposed communicant sensor (CS). Then an impedance based algorithm is applied only at the faulty MLS. To examine the whole method in the field, a real PDS from the Algerian distribution grid is used. Experimental results present significant benefits compared to a previous method reported in the literature.
  • No Thumbnail Available
    Item
    Document clustering analysis based on hybrid cuckoo search and K-means algorithm
    (IEEE, 2021) Boushaki, Saida Ishak; Bendjeghaba, Omar; Brakta, Noureddine
    The clustering is an interesting technique for unsupervised document organization in the World Wide Web (WWW). The most widely used partitioning clustering algorithm is K-means. However, it has an issue with random initialization, which might lead to local optimum situations. In fact, metaheuristics-based clustering has demonstrated their efficiency to reach a global solution instead of local one. The Cuckoo search (CS) has been widely used for the clustering problem. However, the number of iterations grows dramatically when the dataset is high dimensional like the documents. In this study, the hybridization cuckoo search and K-means algorithms for the document clustering are analyzed. So, three hybrid algorithms are investigated and compared. The performance and the efficiency of the proposed algorithms are evaluated using Reuters 21578 Text Categorization Benchmark Dataset. The obtained results show the capability of the new approaches to generate more compact clustering and enhancing purity and F-measure clustering qualities
  • No Thumbnail Available
    Item
    Dips detection techniques discussion
    (IEEE, 2021) Brakta, Noureddine; Bendjeghaba, Omar; Yazid Zidani, Mohamed Yazid
    In today's industrial world, renewable energy represents 16% of the total produced and consumed energy. Wind energy is gaining popularity and imposing bigger footprint in the natural sources of electricity and plays a key building block for economic recovery from the impact of COVID-19 according to the Global wind Energy Council. Yet, because its presence in the energy resource share is below 5%, since most of the wind farms use Doubly Fed Induction Generator (DFIG) it will suffer from grids faults such as symmetric dips. The scary part of the dips is that it will increase the currents at the back-to-back converters and even when dealing with them oscillation might destroy the turbine and generator assembly. In this paper we will review techniques used to detect the dips and override the heavy increase of the current using a crowbar, we will concentrate only on the detection and compare the resulting parameters while keeping the controllers and the value of the crowbar resistance unchanged
  • No Thumbnail Available
    Item
    Accelerated modified sine cosine algorithm for data clustering
    (IEEE, 2021) Boushaki, Saida Ishak; Bendjeghaba, Omar; Brakta, Noureddine
    In artificial intelligence, data mining is a process that automatically discover valuable information from huge amounts of data in order to obtain knowledge. The most important unsupervised technique of data mining is the clustering technic, which his main task is dividing the dataset into homogeneous groups. Metaheuristics based clustering is an actual research area where optimization algorithms have demonstrated their efficiencies to provide near optimal solutions to this problem in a reasonable time, including the recent Sine Cosine metaheuristic Algorithm (SCA). However, its convergence rate is still rather slow. In this paper, an upgraded adaptation of SCA is proposed to improve the exhibition capacities of the quest strategy for ideal results for data Clustering problem, named AMSCAC. In this algorithm, both the local and global search procedures are enhanced by additional strategy. The experimental results on five standard datasets are promising and confirm the superiority of AMSCAC, for the clustering results over SCA, cuckoo search algorithm (CS), differential evolution algorithm (DE), and genetic algorithm (GA)
  • No Thumbnail Available
    Item
    Dynamic Performance Improvement of DFIM based on Hybrid Computational Technique
    (IEEE, 2021) Zidani, Mohamed Yazid; Brakta, Noureddine; Bendjeghaba, Omar
    This paper presents a hybrid intelligent nonlinear control, based on particle swarm optimization (PSO) technique and artificial intelligence controller (AI) to improve the dynamic performance of the system. These controllers are destined for the speed control of Doubly Fed Induction Motor (DFIM). The proportional-integral controller for speed regulation of the induction motor is the most extensively used controller. However, given the various operating conditions and the nature of parameter variability, the PI controller has some drawbacks. So, one of the frequently discussed applications of artificial intelligence (AI) in control is the replacement of a proportional integral speed controller with Artificial Neural Network (ANN) speed controller but the choice of the gain’s parameters controller is one of the main problems. So, Particle Swarm Optimization (PSO) technique on optimization performance is added to the PI and ANN controllers to find the best gain values. The simulation results for different scenarios illustrate the high performance of the proposed artificial intelligence controller for DFIM running at variable speeds in terms of consistency and stability
  • No Thumbnail Available
    Item
    Improved Cuckoo Search Algorithm for Document Clustering
    (SPRINGER, 2015) Ishak Boushak, Saida; Kamel, Nadjet; Bendjeghaba, Omar
    Efficient document clustering plays an important role in organizing and browsing the information in the World Wide Web. K-means is the most popular clustering algorithms, due to its simplicity and efficiency. However, it may be trapped in local minimum which leads to poor results. Recently, cuckoo search based clustering has proved to reach interesting results. By against, the number of iterations can increase dramatically due to its slowness convergence. In this paper, we propose an improved cuckoo search clustering algorithm in order to overcome the weakness of the conventional cuckoo search clustering. In this algorithm, the global search procedure is enhanced by a local search method. The experiments tests on four text document datasets and one standard dataset extracted from well known collections show the effectiveness and the robustness of the proposed algorithm to improve significantly the clustering quality in term of fitness function, f-measure and purity.
  • No Thumbnail Available
    Item
    Improved cuckoo search algorithm for document clustering
    (Springer, 2015) Boushaki, Saida Ishak; Kamel, Nadjet; Bendjeghaba, Omar