A Near real time system to determine a cost-effective IDD traffic routing plan

Abstract

International telecommunication has become a very important sector in the present day communication. IDD traffic is one of the main sources of revenue for national telecommunication service providers (Telcos). Hence, it has to be managed properly and driven effectively to gain maximum profit./ Telco’s usually deal with multiple international operators (carriers) e.g. SingTel, Telstra, in order to use latter's networks for international traffic. These carriers offer different charging structures which vary with the time, volume and the destination. Most Telcos incur high costs due to lack of a proper system to analyse and forecast an optimized IDD routing plan./ Therefore, a system which is capable of producing a cost-effective routing plan by analyzing the current IDD usage pattern and the traffic cost would be much beneficial for all Telco’s. The objective of this research work is to find a suitable methodology for Telcos to produce a cost-effective routing plan for the IDD traffic in near real time. In our approach, the main tasks are, • Forecasting the IDD traffic pattern to each destination • Determining the optimized routing plan. Forecasting the future traffic was based on past traffic, current IDD traffic trend and the subscriber growth rate of Telcos. A Genetic Algorithm (GA) was used to obtain the optimized routing plan. Dynamic behavior of the problem domain was successfully addressed in the GA structure./ The GA parameters, population size, number of generations and the GA operations (crossover, mutation and reproduction) ratio were determined experimentally. Experimental results show that our solution is capable of producing a cost-effective routing plan in near-real-time which reduces the cost by 30% to 50% against the manual routing plan. Our solution could be used by national Telco’s to save significant costs in the international traffic and to pass some of that cost savings to their customers.