Please use this identifier to cite or link to this item:
|Title||Interference Management in OFDMA Femtocell Network|
|Title in Arabic||ادارة التدخلات في نظام ofdma بشبكات الفيمتو|
The next generation cellular wireless network aims to efficiently deploy low cost and low power cellular base station in the subscriber’s indoor environment. Also, one of the effective techniques of improving the coverage and enhancing the capacity and data rate in cellular networks is to reduce the cell size and transmission distances. Therefore, the concept of deploying femtocells over macrocell has recently attracted growing interests in academia and in telecommunication operators. Interference management becomes a major issue in the deployment of femtocells because they share the same licensed frequency spectrum with macrocell, so there are interference between neighboring femtocells called Co-tier interference and between the femtocell and macrocell called Cross-tier interference. Wherefore, the demand increases for mitigation interference techniques. Femtocell may not be possible to carry out an elaborate frequency planning of the femtocell network so they are expected to have self-configuring ability. In this study, we proposed an adaptive Co-tier and Cross-tier interference avoidance scheme by self-organization using reinforcement learning in orthogonal frequency division multiple access (OFDMA). We developed an autonomous radio resource (RB) allocation algorithm to pursue the most efficient frequency allocation. In order that, self-organized power and resources block allocation technique solved the interference problem caused by a femtocell network operating in the same channel in cellular network. We consider modeling the femto network as a multi agent system where each femto base stations is the agent in charge of managing the radio resources to be allocated to their femtousers. So, real-time multi-agent reinforcement learning, known as decentralized Q-learning, to manage the interference generate to femto/ macro-users with no more traffic in backbone network. In order that, the agent is interacting with the surrounding environment in a distributed fashion so that is able to learn an optimal policy to solve the interference problem.
|Publisher||الجامعة الإسلامية - غزة|
|Files in this item|