Task scheduling in mobile edge computing (MEC) is critical for managing latency and energy consumption, especially under user mobility, which poses additional challenges to scheduling decisions. This paper studies the mobility-aware two-stage task scheduling (MTTS) problem in MEC systems to minimize energy consumption at the mobile edge under task deadline constraints. First, the MTTS problem is formulated as a two-stage optimization model consisting of two interrelated sub-problems, associated with task offloading and result downloading, respectively. Then, a dual-population-based evolutionary computation (DORA) framework is proposed that can solve MTTS-type two-stage problems by incorporating a wide range of swarm intelligence algorithms (SIAs). The proposed DORA framework employs two populations that run in parallel, each dedicated to solving one of the two interrelated sub-problems, to enable effective exploration of the solution space and improve computational efficiency. The evolutionary process of each population in DORA consists of three fundamental algorithmic components: mapping, evaluation, and updating. In particular, the mapping component establishes the link between individual space in SIAs and solution space in the MTTS problem, with the critical parameter derived through rigorous theoretical analysis. Furthermore, the inter population collaboration is realized through an asynchronous solution transfer mechanism from the stage-1 population to the stage-2 population, guiding the search toward high-quality final scheduling solutions. Extensive experiments are conducted on a real-world mobile device trajectory dataset, incorporating four well-established SIAs to demonstrate the applicability and effectiveness of DORA.

When designing task scheduling algorithms in mobile edge computing (MEC), the mobile device (MD)’s mobility becomes an important concern, since the change in MD’s location would affect the data transmission rate, leading to fluctuations in task transmission duration and completion time. In this article, we study a mobility-aware task off-and-downloading scheduling problem in MEC, considering both the communication delay and energy consumption caused by the data offloading and the result downloading. We first formulate a mathematical optimization model of the studied problem and prove its NP-hardness. To explore high-quality task scheduling decisions, we propose a swarm intelligence algorithm-based evolutionary computation (START) framework. The main technical innovations of START include a solution representation of off-and-downloading sequence, an exponential probability model-based mapping operator, and a task dispatching heuristic. Specifically, the solution representation makes START applicable to a wide range of swarm intelligence algorithms. The mapping operator establishes the link between individual space and solution space, in which the critical parameter is determined by a rigorous theoretical analysis. The task dispatching strategy is the only component of the START framework that is relevant to the particular problem, providing the extensibility of applying START to solving other problems. In experiments, we create a real-world MD trajectory dataset MDT-NJUST, and integrate several representative swarm intelligence algorithms to justify the performance of START in solving the scheduling problem. Experimental results also verify the conclusion drawn from the theoretical analysis on critical parameter determination.

In cloud-edge computing paradigms, the integration of edge servers and task offloading mechanisms has posed new challenges to developing task scheduling strategies. This paper proposes an efficient convergent firefly algorithm (ECFA) for scheduling security-critical tasks onto edge servers and the cloud datacenter. The proposed ECFA uses a probability-based mapping operator to convert an individual firefly into a scheduling solution, in order to associate the firefly space with the solution space. Distinct from the standard FA, ECFA employs a low-complexity position update strategy to enhance computational efficiency in solution exploration. In addition, we provide a rigorous theoretical analysis to justify that ECFA owns the capability of converging to the global best individual in the firefly space. Furthermore, we introduce the concept of boundary traps for analyzing firefly movement trajectories, and investigate whether ECFA would fall into boundary traps during the evolutionary procedure under different parameter settings. We create various testing instances to evaluate the performance of ECFA in solving the cloud-edge scheduling problem, demonstrating its superiority over FA-based and other competing metaheuristics. Evaluation results also validate that the parameter range derived from the theoretical analysis can prevent our algorithm from falling into boundary traps.