By increasing the number of IoT-devices, cloud-computing faces challenges for some computation and time-sensitive applications. Edge-computing has emerged to enable IoT-devices offload their computation tasks. Offloading tasks is a complex and challenging issue. We propose a comprehensive model including user, edge and cloud layers for scheduling continuous offering of services. Furthermore, we modeled the tasks of service as recurrent (repetitive) with a given frequency. The service-placement problem is formulated as a Mixed-Integer Linear Programming problem that aims to minimize the total delay of all services. We solve the problem with CPLEX, and proposed four fast heuristics to find near-optimal solutions. We compared the results of our proposed heuristics with the result obtained with CPLEX, in terms of problem-solving speed and accuracy, as well as resource utilization of all nodes. The results show that two of our proposed heuristics produce near-optimal solutions in a fraction of the time taken by CPLEX.

Due to cloud computing's limitations, edge computing has emerged to address computation-intensive and time-sensitive applications. In edge computing, users can offload their tasks to edge servers. However, the edge servers' resources are limited, making task scheduling everything but easy. In this paper, we formulate the scheduling of tasks between the user equipment, the edge, and the cloud as a Mixed-Integer Linear Programming (MILP) problem that aims to minimize the total system delay. To solve this MILP problem, we propose an Enhanced Healed Genetic Algorithm solution (EHGA). The execution time of EHGA is shortened in two ways: First, after the crossover and mutation, EHGA heals rather than discards the failed offspring. Second, EHGA divides the chromosome into several sub-chromosomes and attempts to discover the optimum solution for each sub-chromosome in parallel. It uses the best solution for each sub-chromosome to generate a new chromosome. The results with EHGA are compared with those of CPLEX and a few heuristics previously proposed by us. The results indicate that EHGA is more accurate and reliable than the heuristics and quicker than CPLEX at solving the MILP problem.

The Internet of Things (IoT) has emerged as a fundamental cornerstone in the digitalization of industry and society. Still, IoT devices’ limited processing and memory capacities pose a problem for conducting complex and time-sensitive computations such as AI-based shop floor monitoring or personalized health tracking on these devices, and offloading to the cloud is not an option due to excessive delays. Edge computing has recently appeared to address the requirements of these IoT applications. This paper formulates the scheduling of tasks between IoT devices, edge servers, and the cloud in a three-layer Mobile Edge Computing (MEC) architecture as a Mixed- Integer Linear Programming (MILP) problem. The paper proposes a simulated annealing-based task scheduling technique and demonstrates that it schedules tasks almost as time-efficient as if the MILP problem had been solved with a mixed integer programming optimization package; however, at a fraction of the cost in terms of CPU, memory, and network resources. Also, the paper demonstrates that the proposed task scheduling technique compares favorably in terms of efficiency, resource consumption, and timeliness with previously proposed techniques based on heuristics, including genetic programming.

This paper presents a novel online task scheduling strategy called SATS, designed for a hierarchical Mobile Edge Computing (MEC) architecture. SATS utilizes a Simulated Annealing-based method for scheduling tasks and demonstrates that Simulated Annealing can be a viable solution for online task scheduling, not just for offline task scheduling. However, the paper also emphasizes that the effectiveness of SATS depends on the precision of service request predictions. The paper evaluates three types of predictors: neutral, conservative, and optimistic. It concludes that when using a conservative predictor that overestimates the number of service requests, SATS performs the best in terms of higher acceptance rates and shorter processing times. In fact, when using a conservative predictor, SATS can offer an acceptance ratio that is only 5% lower than what it could have been if SATS had known the frequency of service request arrivals beforehand and deviates less than 20% from this acceptance ratio in all conducted experiments.

Mobile Edge Computing (MEC) enables latency-sensitive Internet of Things (IoT) applications by offloading computation to nearby edge servers. However, most existing intelligent scheduling approaches either neglect the full three-tier device–edge–cloud architecture or fail to account for heterogeneous IoT services composed of multiple dependent tasks with diverse deadlines and resource demands. These gaps hinder adaptability under dynamic network conditions. We propose a multi-agent reinforcement learning (MARL) framework in which cellular IoT devices and the edge server act as cooperative agents to optimize task offloading and scheduling. Each agent employs a multi-head deep Q-network (MH-DQN)—with one head per service type—to efficiently manage heterogeneous service workflows. We further implement a multi-head Double DQN (MH-DDQN)variant to improve stability and convergence. In addition, we benchmark our approach against four heuristic baselines and an adaptive simulated annealing (SA) scheduler. Simulation results demonstrate that both MH-DQN and MH-DDQN substantially outperform the heuristic baselines, and that the learned policies match or slightly exceed the SA acceptance ratio while achieving noticeably lower processing times, maintaining high deadline compliance (up to approximately 85% acceptance at heavy load), and reducing latency. MH-DDQN achieves the fastest convergence, greater stability, and slightly lower delays, highlighting its advantage for adaptive scheduling in complex MEC environments.