Efficient Extreme Gradient Boosting Based Algorithm for QoS Optimization in Inter-Radio Access Technology Handoffs

Abstract

The deployment of many base stations within a small network coverage area can potentially increase network capacities. However, this implies frequent handoffs as the users move within the small tracking areas. An effective hand off strategy is therefore required to boost quality of service and quality of experience during the handoff process. Unfortunately, most of the conventional handoff strategies are reactive and tend to deploy single or few parameters as inputs to the decision-making process. As such, handoffs are executed without fully considering user satisfaction as well as application, device and service requirements. This results in deterioration of both quality of service and quality of experience after the handoff procedures. In this paper, extreme gradient boosting based algorithm is presented. The results show that it has minimal handoff failure and ping pong rates, while exhibiting very high handoff success rates. In addition, its receiver operating characteristic-area under curve value of 0.97627 exceeds the 0.7 threshold. Consequently, it is capable of predicting the success of the inter-radio access technology handoff with high probability.