Neural network

yasdama's picture

Self-Organizing Schedulers in LTE System for Optimized Pixel Throughput Using Neural Network

Year of Publication: 
2015
Authors: 
Jehad Hamamreh
Department of Telecommunication Engineering, Faculty of Engineering and Information Technology, An-Najah National University, Nablus. Palestine
Nader Menawi
Department of Telecommunication Engineering, Faculty of Engineering and Information Technology, An-Najah National University, Nablus. Palestine
Awni Natshi
Department of Telecommunication Engineering, Faculty of Engineering and Information Technology, An-Najah National University, Nablus. Palestine
Allam Mousa
Department of Telecommunication Engineering, Faculty of Engineering and Information Technology, An-Najah National University, Nablus. Palestine
Falah Hasan
Department of Telecommunication Engineering, Faculty of Engineering and Information Technology, An-Najah National University, Nablus. Palestine
Yousef Dama
Department of Telecommunication Engineering, Faculty of Engineering and Information Technology, An-Najah National University, Nablus. Palestine
Khaled Hijjeh
Telecom. Eng. Dep., An-Najah National University.
Preferred Abstract (Original): 

One of the most important requirements for Long Term Evolution (LTE) is minimizing the costs and effort of network planning, optimization and configuration to the lowest possible level, while keeping a very good acceptable performance level which can be achieved by using self-organizing networks (SON) concept. This paper presents an efficient technique to train base station (E-NodeB) in order to choose the most appropriate and optimized scheduler in LTE system for each pixel inside an image using Neural Network technique, which leads to an optimized bandwidth and hence increased capacity. The simulation results using our proposed method using self-organizing assigning scheduler indicate an overall 33% saving in

Hikmat S. Hilal's picture

Modelling and Simulation of Ingap Solar Cells Under Solar Concentration: Series Resistance Measurement and Prediction

Journal Title, Volume, Page: 
Solid State Sciences, Volume 8, Issue 5,Pages 556-559
Year of Publication: 
2006
Authors: 
H.S. Hilal
An-Najah N. University, P.O. Box 7, Nablus, West Bank, Palestine
Current Affiliation: 
Department of Chemistry, An-Najah N. University, Nablus, PO Box 7, West Bank, Palestine
A. Cheknane
Unité de Recherche des Matériaux et Energies Renouvelables, Université Abou Bakr Belkaid Tlemcen, Algérie
J.P. Charles
MOPS, SUPELEC, 2 rue Edouard Belin, 57070 Metz, France
B. Benyoucef
Unité de Recherche des Matériaux et Energies Renouvelables, Université Abou Bakr Belkaid Tlemcen, Algérie
G. Campet
CNRS, Université Bordeaux I, Château Brivazac, Ave du Dr. A. Schweitzer, 33600 Pessac, France
Preferred Abstract (Original): 

One of the important parameters, that commonly affect solar cell performances, is the series resistance. Such effect becomes more pronounced when working under higher illumination intensities due to higher generated photocurrents. Therefore, it is necessary to predict series resistance effects under such conditions. To know more about the series resistance effect and its interpretation, InGaP based solar cell performances were investigated, using high solar concentration levels (73.36 X, 201.19 X). To facilitate the prediction of series resistance effect, as a function of insolation level, a computerised analytical model, using neural network, is presented.

 SERIES RESISTANCE MEASUREMENT AND PREDICTION
 

Syndicate content