CompCube: A Space-Time-Request Resource Trading Framework for Edge-Cloud Service Market

Abstract

As the footing stone of artificial intelligence (AI), ubiquitous computing resource is beginning to receive interest. With this trend, a new form of edge-cloud service market dedicated to collecting, trading, and scheduling computing resources is rising. The computing participants in the service market, as providers and demanders of computing resources, are becoming more diversified and open. As such, the intriguing economic phenomenon and the circulation mechanism have emerged. These bring inherent challenges, such as a volatile market, the ossification of pricing, isolation, and inefficiency. In this paper, we propose a novel space-time-request trading framework for the edge-cloud service market, namely <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CompCube</i> . To ensure stability, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CompCube</i> adopts the dual-circulation futures-spot trading method, including space-time dynamic pricing in the macro-cycle, request intention conversion, and resource matching in the micro-cycle. Among this, an incomplete information game model is designed to determine the long-term trading pricing in the macro-cycle. Then, to tackle the indicator isolation problem due to the inconsistency between the user's requests and the computing-power provider's (CPP's) resources, we focus on minimizing the rental cost of computing resources while satisfying diverse service level agreements (SLA) of users. To address this problem, a spatiotemporal scale Lyapunov optimization and an alternating actor-critic algorithm, A2SC, are developed. Besides, in the micro-cycle, a discriminatory double auction helps to determine the computing resource matching results efficiently and impersonally. We evaluate the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CompCube</i> of the A2SC algorithm with realistic datasets. Compared to other baselines, i.e., DYRECEIVE, Price Preferred, and Random, A2SC reduces the average rental cost by 30.45%, 5.74%, and 17.57%, respectively. Furthermore, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CompCube</i> can improve SLA satisfaction, as well as promote resource efficiency and social welfare compared with the traditional methods.