Design of ANN Based Handover Chip using VHDL
Loading...
Files
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In order to meet the escalating requirements for wireless communication servIces, smaller cells are deployed to boost the traffic capacity in limited spectrum allocation. But, with the decrease in cell size, the number of cell boundary crossings by the user i.e. Mobile Station (MS) also increase. Consequently, the number of handoffs, process that transfers an ongoing call from one cell to another, also increases rapidly. These handoffs should be imperceptible to the users and also the quality of service (QOS) should be maintained throughout. The performance of the cellular systems is heavily influenced by the handover schemes.
Thus, we may observe the complexity associated with the handoff decision. It is indeed, a complicated task to predict accurately the need of handoff and also to execute it efficiently. Hence, there exists a need to develop an intelligent system that would predict the requirement of handoff to a much greater degree of accuracy. Also, this system should be capable to perform the handoff at a faster rate than the existing ones. This intelligence can be given to the system using one of the emerging technologies such as fuzzy logic, neural networks, particle swarm optimization etc. In this work, we have used the Neural Networks, which have a far reaching potential as building blocks in tomorrow's computational world.
In this thesis, the hardware implementation of neural networks based on digital components is done. A generalized Neural Network is designed in a Hardware, Description Language i.e. VHDL, which enables us to get the entire design on a chip.
Perhaps the most promising approach in emulating neural models digitally is the Field Programmable Gate Array (FPGA). Hence, the design is chosen to be implemented on an FPGA.
The design of handoff circuit can be converted to a parallel processing system that can monitor all the MSs being served in the cell. Being parallel in nature the processing speed goes up tremendously thereby, improving the quality of service (QoS). Also the circuit can be embedded in MS leading to Mobile Controlled Handoff.
