Auction-based Edge Cloud Deadline-aware Task Offloading Strategy

Abstract

With the advent of the Internet of everything and the 5G era,the amount of data that mobile users need to process does not match their data processing capabilities,offloading a large number of tasks to limited edge servers for execution is bound to produce competition.The introduction of auction modelcan solve the problem of resource competition among users.At present,most task offloading works based on auction ignore the deadline perception of tasks,the general task offloading work only consi-ders delay-sensitive tasks,and does not consider ensuring the security of the offloading process.Therefore,an auction based deadline-aware task offloading(ABDTO) strategy is proposed,which uses the auction mechanism based on smart contract to realize the optimal allocation of deadline-aware tasks(delay-sensitive tasks and non-delay-sensitive tasks) to the edge ser-vers,and the total utility(i.e.total profit) is taken as the evaluationcriterion to achieve a win-win situation between mobile users and edge ser-vers.The heuristic genetic algorithm is used to conduct simulation experiments.Compared with TACD,UPPER and RND algorithms,ABDTO strategy has higher overall utility.Finally,using Remix,Ganache,etc.to establish the Ethereum private blockchain network for simulation,which proves the correctness and feasibility of the strategy.

Keywords

• edge cloud|auction mechanism|deadline aware|task offloading|smart contract