Litcius/Paper detail

A Trust-Based Computation Offloading Framework in Mobile Cloud-Edge Computing Networks

Jianhui Wang, Zhetao Li, Haolin Liu, Tie Qiu, Hongbin Luo

2025IEEE Transactions on Mobile Computing12 citationsDOI

Abstract

Cloud service centers (CSCs) can purchase edge computation resources to improve service quality in mobile cloud-edge computing networks. However, edge servers (ESs) are owned by different entities, and dishonest entities may launch computational forgery attacks, i.e., the ES falsely reports its idle computation resources to win more tasks for increased revenue. Most existing approaches ignore the threat of dishonest ESs. To address the challenges, we design a <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T</u>rust-based <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</u>omputation <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</u>ffloading (TCO) framework. First, we construct the problem for minimizing the <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">d</u>ifference between the CSC's <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">c</u>ost and the <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e</u>xpected <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">r</u>evenue (DCER), which is a mixed-integer nonlinear programming problem. Second, we develop a trust-based computation offloading method that quickly finds a good solution by decomposing the problem. Finally, a two-tier trust evaluation method was proposed to obtain accurate trust values. Experimental results indicate that TCO's comprehensive performance surpasses the benchmarks and significantly enhances computation offloading reliability with a lower performance loss. Notably, tasks are preferentially offloaded to honest ESs to ensure their revenue and promote ESs’ honesty under the TCO framework. Additionally, compared with no trust mechanisms, TCO reduces the service timeout count in an interval by 34.37% - 73.80% with a performance loss of only 1.42% - 4.10%.

Topics & Concepts

Computer scienceComputation offloadingCloud computingMobile cloud computingMobile edge computingMobile computingDistributed computingEdge computingComputationComputer networkEnhanced Data Rates for GSM EvolutionArtificial intelligenceOperating systemAlgorithmIoT and Edge/Fog ComputingCloud Data Security SolutionsBlockchain Technology Applications and Security