Enhancing the performance of multi-access edge computing based intelligent transportation system
Year: 2026
Type: article
Abstract: Vehicle-based Intelligent Transportation Systems (ITSs) utilize connected vehicles to enhance our driving experience and optimize traffic flow. However, most vehicles do not have the processing capability necessary to support the expanding number of increasingly complex technologies associated with ITS. Examples of this include real-time traffic analysis and autonomous driving features. Multi-access Edge Computing (MEC) provides a possible solution to the issue of offloading computation from vehicles by utilizing minicomputer servers located at the edge of the network, where the action is happening. This enables vehicles to offload large computations onto these MEC servers and increase their available resources, thereby improving overall system performance. In addition, caching of frequently used data within the MEC servers can also alleviate the processing burden on vehicles. The optimization of the strategy to fully implement MEC applications is critical. The proposed paper presents a combined optimization of service caching and computational offloading strategies for MEC-based Intelligent Transportation Systems that are located within Small Cell Networks. This methodology utilizes a Best-Score Server Selection Algorithm (BSSSA) approach, which assesses MEC servers to determine server scores based on pre-cached tasks, available resources, latency from the operator to the server, and proximity to the operator (vehicle). The server with the highest score is utilized for the physical offload of tasks. With Least Recently Used as the cache replacement policy on MEC servers, the content in these servers can be efficiently managed to maintain a maximum cache hit ratio, resulting in reduced overall system latency and energy consumption by the mitigation of duplicate tasks executed by the same MEC servers. By utilizing existing server capabilities, latency, and proximity of the operator (vehicle) through BSSSA, a significant increase in Packet Delivery Ratio (PDR) will be provided, which allows for reliable transmission of packets. In addition, the overall performance of the MEC networks can be improved, as the use of Software Defined Network (SDN) technology will provide efficient information collection and centralized management of the vehicular network, as the primary purpose of an MEC network is to support high-speed data transportation. To benchmark the effectiveness of this proposed methodology, real-world vehicle-to-network scenarios will be created and tested by utilizing the OMNeT + + network simulation tool in conjunction with the Simu5G modules for 5G vehicular communication and the OpenFlow protocol, which facilitates the use of SDN technologies. The proposed methodology is expected to result in high cache hit ratios, low computing energy use of MEC servers, low latency in offloading tasks, and overall improved system performance and reliability.
Source: Scientific Reports
Language: English
Topic: IoT and Edge/Fog Computing
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,690
OpenAlex ID: W7233540666
