A Repeated Auction Model for Load-Aware Dynamic Resource Allocation in Multi-Access Edge Computing

Multi-access edge computing (MEC) is one of the enabling technologies for high-performance computing at the edge of the 6 G networks, supporting high data rates and ultra-low service latency. Although MEC is a remedy to meet the growing demand for computation-intensive applications, the scarcity of resources at the MEC servers degrades its performance. Hence, effective resource management is essential; nevertheless, state-of-the-art research lacks efficient economic models to support the exponential growth of the MEC-enabled applications market. We focus on designing a MEC offloading service market based on a repeated auction model with multiple resource sellers (e.g., network operators and service providers) that compete to sell their computing resources to the offloading users. We design a computationally-efficient modified Generalized Second Price (GSP)-based algorithm that decides on pricing and resource allocation by considering the dynamic offloading requests arrival and the servers’ computational workloads. Besides, we propose adaptive best-response bidding strategies for the resource sellers, satisfying the symmetric Nash equilibrium (SNE) and individual rationality properties. Finally, via intensive numerical results¹, we show the effectiveness of our proposed resource allocation mechanism.

I. Introduction

The large-scale deployment of intelligent wireless applications involves numerous computationally-intensive and latency-critical tasks. Although advanced smart devices possess a significant processing capacity, they suffer from limited battery life. Besides, the centralized cloud computing infrastructure is not viable due to long propagation delays, thus a low quality-of-service (QoS). To face this challenge, Mobile Edge Computing, also called Multi-access Edge Computing (MEC) emerges offering computing capabilities at the edge of the radio access network (RAN) [1]. In the MEC framework, the computing servers are in the proximity of data sources, i.e. user equipment (UE), and computational tasks are executed by harvesting idle computing resources and storage from the edge servers. Thus, the end-to-end communication delay reduces significantly, which makes MEC the prominent choice for provisioning emerging wireless applications. These include over-the-top multi-media streaming services [2], online interactive games [3], augmented and virtual reality, and tactile internet [4], and video analytic [5]. The MEC concept enables wireless service- and infrastructure providers to access heterogeneous fixed and mobile wireless access technologies in WiMax, 4 G/LTE, 5 G networks, and beyond through software-based services, security solutions, and network functionalities. That facilitates the integration of MEC with the existing 3GPP network architecture without making significant changes to the hardware infrastructure [6]. A MEC system is deployable using the RAN elements such as base stations (BSs), access points (APs), and gateways, which typically host the MEC application programming interfaces (APIs) [7]. A MEC system is also implementable in central locations such as data centers of network operators or on moving nodes like passenger vehicles or UAVs. As such, a MEC system can utilize local radio-network contextual information to guarantee secure, reliable, and privacy-preserving services based on intelligent analysis and data processing capabilities at the edge [8].