@techreport{oai:ipsj.ixsq.nii.ac.jp:00233071,
 author = {Massinissa, Lakhdar Friha and Hideaki, MIiyaji and Hiroshi, Yamamoto and Massinissa, Lakhdar Friha and Hideaki, MIiyaji and Hiroshi, Yamamoto},
 issue = {51},
 month = {Mar},
 note = {In the rapidly evolving landscape of mobile networks, the integration of Multi-access Edge Computing (MEC) with 5G technology presents a transformative approach to network architecture. Existing network architectures centered around cloud-based processing encounter bottlenecks due to centralized servers, resulting in higher latency and bandwidth constraints that impede real-time data processing. The proposed architecture proposes the utilization of edge servers as a solution, decentralizing the computational load to enhance responsiveness and reduce latency within 5G networks. This paper outlines the conceptual framework and simulation of such an integration, aiming to enhance the quality of service and user experience through reduced latency and improved computational efficiency. Utilizing the OMNeT++ simulation platform, this research constructs a detailed representation of a 5G network environment. The integration of the Simu5G and INET libraries further strengthens the simulation that provides comprehensive models for 5G network functionalities alongside Multi-Access Edge Computing. The core of the proposed architecture is the MEC Orchestrator, a system that manages the computing resources at the network’s edge. It interfaces with multiple MEC Hosts, which are small servers positioned at the edge of the network. These MEC hosts are tasked with processing data and delivering services in close proximity to the user, significantly cutting down on latency. In our research, we focus on establishing the network’s architecture, simulating the dynamic interactions between a User Equipment (UE) of a mobile user and the MEC infrastructure, and the research anticipate the development of a predictive algorithm designed to predict the future position of the User Equipment (UE). This future prediction algorithm is expected to orchestrate the selection of the optimal MEC Host for processing user tasks based on the predicted location of the UE. It leverages historical and real-time location data, aiming to ensure that data processing occurs at the network’s edge nearest to the user’s future location., In the rapidly evolving landscape of mobile networks, the integration of Multi-access Edge Computing (MEC) with 5G technology presents a transformative approach to network architecture. Existing network architectures centered around cloud-based processing encounter bottlenecks due to centralized servers, resulting in higher latency and bandwidth constraints that impede real-time data processing. The proposed architecture proposes the utilization of edge servers as a solution, decentralizing the computational load to enhance responsiveness and reduce latency within 5G networks. This paper outlines the conceptual framework and simulation of such an integration, aiming to enhance the quality of service and user experience through reduced latency and improved computational efficiency. Utilizing the OMNeT++ simulation platform, this research constructs a detailed representation of a 5G network environment. The integration of the Simu5G and INET libraries further strengthens the simulation that provides comprehensive models for 5G network functionalities alongside Multi-Access Edge Computing. The core of the proposed architecture is the MEC Orchestrator, a system that manages the computing resources at the network’s edge. It interfaces with multiple MEC Hosts, which are small servers positioned at the edge of the network. These MEC hosts are tasked with processing data and delivering services in close proximity to the user, significantly cutting down on latency. In our research, we focus on establishing the network’s architecture, simulating the dynamic interactions between a User Equipment (UE) of a mobile user and the MEC infrastructure, and the research anticipate the development of a predictive algorithm designed to predict the future position of the User Equipment (UE). This future prediction algorithm is expected to orchestrate the selection of the optimal MEC Host for processing user tasks based on the predicted location of the UE. It leverages historical and real-time location data, aiming to ensure that data processing occurs at the network’s edge nearest to the user’s future location.},
 title = {Selection Method of Suitable Multi-Edge Computing Server based on Position Prediction of Mobile Users},
 year = {2024}
}