MCDS: AI Augmented Workflow Scheduling in Mobile Edge Cloud Computing Systems

Workflow scheduling is a long-studied problem in parallel and distributed computing (PDC), aiming to efficiently utilize compute resources to meet user's service requirements. Recently proposed scheduling methods leverage the low response times of edge computing platforms to optimize application Quality of Service (QoS). However, scheduling workflow applications in mobile edge-cloud systems is challenging due to computational heterogeneity, changing latencies of mobile devices and the volatile nature of workload resource requirements. To overcome these difficulties, it is essential, but at the same time challenging, to develop a long-sighted optimization scheme that efficiently models the QoS objectives. In this work, we propose MCDS: Monte Carlo Learning using Deep Surrogate Models to efficiently schedule workflow applications in mobile edge-cloud computing systems. MCDS is an Artificial Intelligence (AI) based scheduling approach that uses a tree-based search strategy and a deep neural network-based surrogate model to estimate the long-term QoS impact of immediate actions for robust optimization of scheduling decisions. Experiments on physical and simulated edge-cloud testbeds show that MCDS can improve over the state-of-the-art methods in terms of energy consumption, response time, SLA violations and cost by at least 6.13, 4.56, 45.09 and 30.71 percent respectively.

[1]  Nicholas R. Jennings,et al.  PreGAN: Preemptive Migration Prediction Network for Proactive Fault-Tolerant Edge Computing , 2021, IEEE INFOCOM 2022 - IEEE Conference on Computer Communications.

[2]  Li-zhen Cui,et al.  A Multiple QoS Constrained Scheduling Strategy of Multiple Workflows for Cloud Computing , 2009, 2009 IEEE International Symposium on Parallel and Distributed Processing with Applications.

[3]  Ying Xie,et al.  Improved Particle Swarm Optimization Based Workflow Scheduling in Cloud-Fog Environment , 2018, Business Process Management Workshops.

[4]  Daniel Krajzewicz,et al.  Recent Development and Applications of SUMO - Simulation of Urban MObility , 2012 .

[5]  Hojung Cha,et al.  Optimizing Energy Efficiency of Browsers in Energy-Aware Scheduling-enabled Mobile Devices , 2019, MobiCom.

[6]  Mei-Hui Su,et al.  Characterization of scientific workflows , 2008, 2008 Third Workshop on Workflows in Support of Large-Scale Science.

[7]  Ali J. Ben Ali,et al.  Edge-SLAM: edge-assisted visual simultaneous localization and mapping , 2020, MobiSys.

[8]  Rajkumar Buyya,et al.  FogBus: A Blockchain-based Lightweight Framework for Edge and Fog Computing , 2018, J. Syst. Softw..

[9]  Gerald Tesauro,et al.  Monte-Carlo simulation balancing , 2009, ICML '09.

[10]  Rajkumar Buyya,et al.  Cost-based scheduling of scientific workflow applications on utility grids , 2005, First International Conference on e-Science and Grid Computing (e-Science'05).

[11]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[12]  Salim Hariri,et al.  Performance-Effective and Low-Complexity Task Scheduling for Heterogeneous Computing , 2002, IEEE Trans. Parallel Distributed Syst..

[13]  Alessandro Vullo,et al.  The Ensembl REST API: Ensembl Data for Any Language , 2014, Bioinform..

[14]  Ryan A. Rossi,et al.  Attention Models in Graphs: A Survey , 2018 .

[15]  Mainak Adhikari,et al.  A Survey on Scheduling Strategies for Workflows in Cloud Environment and Emerging Trends , 2019, ACM Comput. Surv..

[16]  Keqin Li,et al.  Efficient task scheduling for budget constrained parallel applications on heterogeneous cloud computing systems , 2017, Future Gener. Comput. Syst..

[17]  Henri Casanova,et al.  WfCommons: A Framework for Enabling Scientific Workflow Research and Development , 2021, Future Gener. Comput. Syst..

[18]  Michael J. O'Grady,et al.  Edge computing: A tractable model for smart agriculture? , 2019, Artificial Intelligence in Agriculture.

[19]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[20]  Reihaneh Khorsand,et al.  Improved many-objective particle swarm optimization algorithm for scientific workflow scheduling in cloud computing , 2020, Comput. Ind. Eng..

[21]  A. Semenov.  Elastic computing self-organizing for artificial intelligence space exploration , 2021 .

[22]  Kotagiri Ramamohanarao,et al.  Dynamic Scheduling for Stochastic Edge-Cloud Computing Environments Using A3C Learning and Residual Recurrent Neural Networks , 2020, IEEE Transactions on Mobile Computing.

[23]  Sai Peck Lee,et al.  Cost-aware challenges for workflow scheduling approaches in cloud computing environments: Taxonomy and opportunities , 2015, Future Gener. Comput. Syst..

[24]  Jiaqing Chen,et al.  A Time-Driven Data Placement Strategy for a Scientific Workflow Combining Edge Computing and Cloud Computing , 2019, IEEE Transactions on Industrial Informatics.

[25]  Rajkumar Buyya,et al.  HUNTER: AI based Holistic Resource Management for Sustainable Cloud Computing , 2021, J. Syst. Softw..

[26]  Jin-Soo Kim,et al.  Cost optimized provisioning of elastic resources for application workflows , 2011, Future Gener. Comput. Syst..

[27]  Thomas Fahringer,et al.  Evolutionary Multi-Objective Workflow Scheduling for Volatile Resources in the Cloud , 2022, IEEE Transactions on Cloud Computing.

[28]  Rajkumar Buyya,et al.  A Particle Swarm Optimization-Based Heuristic for Scheduling Workflow Applications in Cloud Computing Environments , 2010, 2010 24th IEEE International Conference on Advanced Information Networking and Applications.

[29]  Guillaume Pierre,et al.  Docker Container Deployment in Fog Computing Infrastructures , 2018, 2018 IEEE International Conference on Edge Computing (EDGE).

[30]  Yun Yang,et al.  A novel directional and non-local-convergent particle swarm optimization based workflow scheduling in cloud-edge environment , 2019, Future Gener. Comput. Syst..

[31]  Adam Belloum,et al.  Execution Time Estimation for Workflow Scheduling , 2014, 2014 9th Workshop on Workflows in Support of Large-Scale Science.

[32]  Raihan Ur Rasool,et al.  Complementing IoT Services Through Software Defined Networking and Edge Computing: A Comprehensive Survey , 2020, IEEE Communications Surveys & Tutorials.

[33]  Youlong Luo,et al.  Cost-effective replication management and scheduling in edge computing , 2019, J. Netw. Comput. Appl..

[34]  Shivananda R. Poojara,et al.  COSCO: Container Orchestration Using Co-Simulation and Gradient Based Optimization for Fog Computing Environments , 2021, IEEE Transactions on Parallel and Distributed Systems.

[35]  Alexandru Iosup,et al.  Statistical Characterization of Business-Critical Workloads Hosted in Cloud Datacenters , 2015, 2015 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing.

[36]  Qun Li,et al.  A Survey of Fog Computing: Concepts, Applications and Issues , 2015, Mobidata@MobiHoc.

[37]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[38]  E. Tilevich,et al.  Win with What You Have: QoS-Consistent Edge Services with Unreliable and Dynamic Resources , 2020, 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS).

[39]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[40]  Rajkumar Buyya,et al.  START: Straggler Prediction and Mitigation for Cloud Computing Environments Using Encoder LSTM Networks , 2021, IEEE Transactions on Services Computing.

[41]  Sanjay P. Ahuja,et al.  A Survey of the State of Cloud Computing in Healthcare , 2012, Netw. Commun. Technol..

[42]  Serge J. Belongie,et al.  Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[43]  Sanjay Misra,et al.  Transformative effects of IoT, Blockchain and Artificial Intelligence on cloud computing: Evolution, vision, trends and open challenges , 2019, Internet Things.

[44]  Prasanta K. Jana,et al.  A novel cost-efficient approach for deadline-constrained workflow scheduling by dynamic provisioning of resources , 2018, Future Gener. Comput. Syst..

[45]  Frank Hutter,et al.  Decoupled Weight Decay Regularization , 2017, ICLR.

[46]  Wolfgang Küchlin,et al.  Cost-Optimized Parallel Computations Using Volatile Cloud Resources , 2019, GECON.

[47]  Luiz Fernando Bittencourt,et al.  Workflow scheduling for SaaS / PaaS cloud providers considering two SLA levels , 2012, 2012 IEEE Network Operations and Management Symposium.

[48]  Xiao Liu,et al.  A Cost-Effective Time-Constrained Multi-workflow Scheduling Strategy in Fog Computing , 2018, ICSOC Workshops.

[49]  Thar Baker,et al.  CLOSURE: A cloud scientific workflow scheduling algorithm based on attack-defense game model , 2020, Future Gener. Comput. Syst..

[50]  David Rolnick,et al.  Experience Replay for Continual Learning , 2018, NeurIPS.

[51]  Nicholas R. Jennings,et al.  Generative Optimization Networks for Memory Efficient Data Generation , 2021, ArXiv.

[52]  Khaled Matrouk,et al.  Scheduling Algorithms in Fog Computing: A Survey , 2021, Int. J. Networked Distributed Comput..

[53]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[54]  Kin K. Leung,et al.  Migrating running applications across mobile edge clouds: poster , 2016, MobiCom.