Specifying the Switching Fabric Capacities of Switched Local Area Networks’ Nodal Devices

ABSTRACT

The designs of switched Local Area Networks (switched LANs) in practice are largely based on heuristics and experience; in fact in many situations, switches are just purchased and installed arbitrarily, without any formal approach or approaches for specifying the buffers’ (memories’) capacities and Switching Fabric Switching and Forwarding Rates (SFSFRs): that is, the switches’ processors’ data processing/transfer rates. This apparently stems from the fact that, empirical formula(s) for performing the specifications of switches’ memories’ capacities and their SFSFRs are presently, from available literature evidence, not available. But the memories’ capacities and SFSFRs determine the energy consumption of these devices: the larger their values, the more the energy that is consumed and vice-versa. Therefore, installing switches with arbitrarily large memories and SFSFRs in switched LANs results in networks that waste energy during operations. Arbitrarily small SFSFRs are also detrimental to LANs, these being the major contributory factors to the sluggishness of networks: which in turn, results in waste in energy consumed by attached hosts. The need to have correctly specified SFSFRs is therefore very important. In this paper, we explain a novel approach that we developed for optimally specifying the SFSFRs of the switches that interconnect users’ hosts in any LAN.

KEYWORDS:

• Switched LAN
• processors’ data transfer rates
• switching fabric switching and forwarding rates
• traffic pipes
• energy consumption

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Monday Ofori Eyinagho

Dr. Monday Eyinagho obtained a B. Sc. Degree in Electronic and Electrical Engineering from the Obafemi Awolowo University, Ile-Ife, Nigeria in 1988. He also holds a Post-Graduate Diploma in Computer Science from the University of Lagos, Lagos, Nigeria (1991), an MBA (General Management) Degree from the River State University of Science and Technology, Port-Harcourt, Nigeria (2003), an M.Sc Degree in Computer Engineering, from the Federal University of Technology, Owerri, Nigeria (2004), and a Ph. D in Computer Engineering from Covenant University, Ota, Nigeria (2011). Dr. Eyinagho has had extensive industrial work experience in a number of corporate organizations. He is currently a Senior Lecturer in the Department of Electrical and Computer Engineering, Afe Babalola University, Ado-Ekiti, Nigeria. Dr. Eyinagho has published scholarly papers in international journals. He is a member of The Nigerian Society of Engineers, a COREN Registered Electronics Engineer, and Life Member, Nigeria Computer Society. His principal research interests are in the areas of developing and implementing microprocessor-based and embedded systems; modeling and performance optimization of Computer and Data Communication Networks, including the bourgeoning IOT. Dr Eyinagho has severally been tasked with Reviewing Assignments by a number of A-class International journals.