Journal of
Engineering and Technology Research

  • Abbreviation: J. Eng. Technol. Res.
  • Language: English
  • ISSN: 2006-9790
  • DOI: 10.5897/JETR
  • Start Year: 2009
  • Published Articles: 185

Full Length Research Paper

Study of load distribution in fully connected client server network using feedback neural network architecture

Manu Pratap Singh1* Avanish Kumar2, Pradeep Kumar3 and Garima Krishna4
  1Department of Computer Science, Institute of Basic Sciences, Ambedkar University, Khandari, Agra (U. P.), India. 2Department of Mathematical Sciences and Computer Science, Bundelkhand University, Jhansi (U. P.), India. 3RPBD, Central Building Research Institute, Roorkee 247667 (U. A.), India. 4Department of Computer Sciences, College of Engineering (COER), Roorkee - 247667 (U. A.), India.
Email: [email protected]

  •  Accepted: 01 March 2010
  •  Published: 30 April 2010



A fully connected client server network reminiscent of a flat group (analogous to a Hopfield type artificial neural network), consisting of a few clients is considered herein. Distinct client nodes are inter-connected in fully connected architecture as in Hopfield’s associative memory model. Weights of connections are symmetric and the states of the clients are bipolar. Stability of such a network can be obtained by using energy function analysis of Hopfield type network. The problem to explore the condition for stability becomes complicated when the server gets connected with the clients, as the connections of the server with the clients are bidirectional but are not symmetric. Hence it does not anymore satisfy the criteria of a Hopfield network to act as an associative memory. In this case the stability is not fixed point stability; rather it is in the form of chaotic or oscillatory states. Under these conditions it is tedious to establish the stability for the entire network in order to determine the optimal load distribution as reflected from connection strengths of the network. This paper explores the stability of clients’ network and subsequently the stability of the entire network after adding the server to investigate correlation.


Key words: Artificial neural network, Hopfield energy function, optimized stability, client-server network.