期刊
IEEE TRANSACTIONS ON MOBILE COMPUTING
卷 21, 期 3, 页码 940-954出版社
IEEE COMPUTER SOC
DOI: 10.1109/TMC.2020.3017079
关键词
Task analysis; Adaptation models; Cloud computing; Stochastic processes; Dynamic scheduling; Processor scheduling; Time factors; Edge computing; cloud computing; deep reinforcement learning; task scheduling; recurrent neural network; asynchronous advantage actor-critic
资金
- Melbourne-Chindia Cloud Computing (MC3) Research Network
- Australian Research Council
The study introduces a real-time scheduler based on A3C for decentralized learning in Edge-Cloud environments across multiple agents. By utilizing the R2N2 architecture to capture various parameters and temporal patterns, it provides efficient scheduling decisions and selects hyperparameters through sensitivity analysis.
The ubiquitous adoption of Internet-of-Things (IoT) based applications has resulted in the emergence of the Fog computing paradigm, which allows seamlessly harnessing both mobile-edge and cloud resources. Efficient scheduling of application tasks in such environments is challenging due to constrained resource capabilities, mobility factors in IoT, resource heterogeneity, network hierarchy, and stochastic behaviors. Existing heuristics and Reinforcement Learning based approaches lack generalizability and quick adaptability, thus failing to tackle this problem optimally. They are also unable to utilize the temporal workload patterns and are suitable only for centralized setups. However, asynchronous-advantage-actor-critic (A3C) learning is known to quickly adapt to dynamic scenarios with less data and residual recurrent neural network (R2N2) to quickly update model parameters. Thus, we propose an A3C based real-time scheduler for stochastic Edge-Cloud environments allowing decentralized learning, concurrently across multiple agents. We use the R2N2 architecture to capture a large number of host and task parameters together with temporal patterns to provide efficient scheduling decisions. The proposed model is adaptive and able to tune different hyper-parameters based on the application requirements. We explicate our choice of hyper-parameters through sensitivity analysis. The experiments conducted on real-world data set show a significant improvement in terms of energy consumption, response time, Service-Level-Agreement and running cost by 14.4, 7.74, 31.9, and 4.64 percent, respectively when compared to the state-of-the-art algorithms.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据