Mobile Computations with Surrounding Devices

Loke, Seng W.; Napier, Keegan; Al‐Ali, Abdulaziz; Fernando, Niroshinie; Rahayu, Wenny

doi:10.1145/2656214

Cited by 37 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Loke et al [39] and Shah [40] addressed the previous limitation by proposing algorithms that do not rely on complete information. This approach seeks to exploit the nodes' proximity and cost-effectiveness of node-transferring capabilities.…”

Section: Human-designed Heuristic Methods In Scesmentioning

confidence: 99%

Solving Task Scheduling Problems in Dew Computing via Deep Reinforcement Learning

et al. 2022

View full text Add to dashboard Cite

Due to mobile and IoT devices’ ubiquity and their ever-growing processing potential, Dew computing environments have been emerging topics for researchers. These environments allow resource-constrained devices to contribute computing power to others in a local network. One major challenge in these environments is task scheduling: that is, how to distribute jobs across devices available in the network. In this paper, we propose to distribute jobs in Dew environments using artificial intelligence (AI). Specifically, we show that an AI agent, known as Proximal Policy Optimization (PPO), can learn to distribute jobs in a simulated Dew environment better than existing methods—even when tested over job sequences that are five times longer than the sequences used during the training. We found that using our technique, we can gain up to 77% in performance compared with using human-designed heuristics.

show abstract

Section: Human-designed Heuristic Methods In Scesmentioning

confidence: 99%

Solving Task Scheduling Problems in Dew Computing via Deep Reinforcement Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…If the public-owned SMDs are utilised to form such clusters, we call it mobile crowd computing (MCC) [8] [9]. The computing-intensive tasks are fanned out to the SMDs, where the assigned tasks are executed, and the results are returned to the MCC coordinator [10] [11]. MCC provides not only a cost-effective HPC but also a significantly energy-efficient HPC option compared to other traditional HPC systems such as supercomputers and cloud data centres [12].…”

Section: Mobile Crowd Computingmentioning

confidence: 99%

Load Balance-Aware Energy-Efficient Scheduling for Mobile Crowd Computing: A PSO-based Solution

Pramanik,

Biswas,

Choudhury

2023

Preprint

View full text Add to dashboard Cite

Due to their increasing computational power and energy-efficient hardware, today's smart mobile devices (SMDs) are replacing desktops and laptops as casual computing devices. Moreover, a cluster of such powerful SMDs can garner substantial high-performance computing (HPC). In mobile crowd computing (MCC), public-owned SMDs are utilised to attain such HPC. Here, a large computing-intensive task is divided and scheduled to the available SMDs for execution and the results are recollected. This provides an economical and sustainable HPC. However, battery-powered constrained energy is a great hindrance to achieving this. Therefore, in MCC, it is crucial to minimise the overall energy consumption to complete the task. This can be achieved to some extent by optimising the task scheduling to the appropriate SMDs. However, considering only energy efficiency might lead to a huge load imbalance among SMDs, i.e., the most energy-efficient SMDs would be overloaded most of the time. Considering this, in this paper, we present a PSO-based scheduling algorithm to minimise the overall energy consumption among a set of SMDs designated to execute a set of MCC tasks while maintaining a satisfactory load balance level. The proposed method is analysed and validated by extensive simulations with synthetic as well as collected datasets. The work is compared with popular heuristic (MCT, MinMin, MaxMin, and PPIA) and metaheuristic (GA) optimisation algorithms, displaying significant improvements over others in terms of the considered objectives. Furthermore, a statistical hypothesis test, ANOVA, is carried out to demonstrate the distinctiveness of the proposed algorithm.

show abstract

“…In [27,28], another kind of scheduler algorithm is proposed that does not need complete knowledge of job requirements to operate. In other words, they do not need the job information that algorithms discussed above require, e.g., job execution time or job energy spent in each candidate node.…”

Section: Related Workmentioning

confidence: 99%

New Heuristics for Scheduling and Distributing Jobs under Hybrid Dew Computing Environments

Sanabria

Tapia

Neyem

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Mobile grid computing has been a popular topic for researchers due to mobile and IoT devices’ ubiquity and their evergrowing processing potential. While many scheduling algorithms for harnessing these resources exist in the literature for standard grid computing scenarios, surprisingly, there is little insight into this matter in the context of hybrid-powered computing resources, typically found in Dew and Edge computing environments. This paper proposes new algorithms aware of devices’ power source for scheduling tasks in hybrid environments, i.e., where the battery- and non-battery-powered devices cooperate. We simulated hybrid Dew/Edge environments by extending DewSim, a simulator that models battery-driven devices’ battery behavior using battery traces profiled from real mobile devices. We compared the throughput and job completion achieved by algorithms proposed in this paper using as a baseline a previously developed algorithm that considers computing resources but only from battery-dependent devices called Enhanced Simple Energy-Aware Schedule (E-SEAS). The obtained results in the simulation reveal that our proposed algorithms can obtain up to a 90% increment in overall throughput and around 95% of completed jobs in hybrid environments compared to E-SEAS. Finally, we show that incorporating these characteristics gives more awareness of the type of resources present and can enable the algorithms to manage resources more efficiently in more hybrid environments than other algorithms found in the literature.

show abstract

Mobile Computations with Surrounding Devices

Cited by 37 publications

References 37 publications

Solving Task Scheduling Problems in Dew Computing via Deep Reinforcement Learning

Solving Task Scheduling Problems in Dew Computing via Deep Reinforcement Learning

Load Balance-Aware Energy-Efficient Scheduling for Mobile Crowd Computing: A PSO-based Solution

New Heuristics for Scheduling and Distributing Jobs under Hybrid Dew Computing Environments

Contact Info

Product

Resources

About