Wednesday 05 March 2025
A team of researchers has made a significant breakthrough in the field of edge computing, developing a new framework for decentralized computation offloading in multi-access edge computing (MEC) systems.
Edge computing is a relatively new concept that involves processing data closer to where it’s generated, rather than sending it all the way back to a central server. This approach can significantly reduce latency and improve overall system performance. However, as more devices and applications rely on edge computing, the need for efficient computation offloading strategies becomes increasingly important.
Computation offloading refers to the process of transferring computational tasks from a device or user equipment (UE) to an edge server, which is typically located closer to the UE. This approach can help reduce power consumption and increase overall system performance by allowing devices to focus on more critical tasks.
The researchers developed a novel framework for decentralized computation offloading in MEC systems using mean-field game (MFG) theory. MFGs are a type of mathematical model that describes the behavior of large populations of agents interacting with each other and their environment.
In this case, the agents are the UEs, which are modeled as non-cooperative players competing for resources at the edge server. The researchers used the MFG framework to compute decentralized policies for each UE to balance between power consumption due to local processor usage and average age of information (AoI) incurred as a result of resource sharing at the edge server.
The AoI is an important metric in communication systems, as it measures the freshness of information being transmitted. The researchers used the AoI to quantify the impact of computation offloading on system performance.
Using simulations, the team validated their theoretical results and observed that increasing the weighting on the AoI portion of the cost can lead to more local processor utilization, while increasing edge server capacity allows UEs to push more computations towards the edge.
The researchers also explored the effect of varying system parameters, such as task arrival rates and edge server capacities, on the performance of their framework. They found that the framework is robust to changes in these parameters and can adapt to different system conditions.
This breakthrough has significant implications for the development of efficient computation offloading strategies in MEC systems. By allowing UEs to make decentralized decisions about when to offload computations and how much to share resources with other devices, the researchers’ framework can help improve overall system performance and reduce power consumption.
Cite this article: “Decentralized Computation Offloading Framework for Multi-Access Edge Computing Systems”, The Science Archive, 2025.
Edge Computing, Computation Offloading, Multi-Access Edge Computing, Decentralized Decision-Making, Mean-Field Game Theory, Non-Cooperative Players, Average Age Of Information, Power Consumption, Local Processor Utilization, System Performance
