Multi-Task Learning-Based Task Scheduling Switcher for a Resource-Constrained IoT System

In this journal, we proposed a novel method of using multi-task learning to switch the scheduling algorithm. With multi-task learning to change the scheduling algorithm inside the scheduling framework, the scheduling framework can create a scheduler with the best task execution optimization under the computation deadline. With the changing number of tasks, the number of types of resources taken, and computation deadline, it is hard for a single scheduling algorithm to achieve the best scheduler optimization while avoiding the worst-case time complexity in a resource-constrained Internet of Things (IoT) system due to the trade-off in computation time and optimization in each scheduling algorithm. Furthermore, different hardware specifications affect the scheduler computation time differently, making it hard to rely on Big-O complexity as a reference. With multi-task learning to profile the scheduling algorithm behavior on the hardware used to compute the scheduler, we can identify the best scheduling algorithm. Our benchmark result shows that it can achieve an average of 93.68% of accuracy in meeting the computation deadline, along with 23.41% of average optimization. Based on the results, our method can improve the scheduling of the resource-constrained IoT system.

[1]  Yu-Jun Zheng,et al.  Real-time neural network scheduling of emergency medical mask production during COVID-19 , 2020, Applied Soft Computing.

[2]  Xing Han,et al.  Visual Sorting of Express Parcels Based on Multi-Task Deep Learning , 2020, Sensors.

[3]  Dalwinder Singh,et al.  Investigating the impact of data normalization on classification performance , 2020, Appl. Soft Comput..

[4]  S Papagiannidis,et al.  Smart offices: A productivity and well-being perspective , 2020, Int. J. Inf. Manag..

[5]  Giancarlo Fortino,et al.  An approach to compute the scope of a social object in a Multi-IoT scenario , 2020, Pervasive Mob. Comput..

[6]  Keith Ord.  Data adjustments, overfitting and representativeness , 2020 .

[7]  Giancarlo Fortino,et al.  A framework for anomaly detection and classification in Multiple IoT scenarios , 2021, Future Gener. Comput. Syst..

[8]  Xu Jiang,et al.  Real-time scheduling of parallel tasks with tight deadlines , 2020, J. Syst. Archit..

[9]  R. Yugha,et al.  A survey on technologies and security protocols: Reference for future generation IoT , 2020, J. Netw. Comput. Appl..

[10]  Junhua Wu,et al.  Methods of Resource Scheduling Based on Optimized Fuzzy Clustering in Fog Computing , 2019, Sensors.

[11]  Chul-Hwan Kim,et al.  Optimal Scheduling of Hybrid Energy Resources for a Smart Home , 2018 .

[12]  Octavia A. Dobre,et al.  Decision Fusion for IoT-Based Wireless Sensor Networks , 2020, IEEE Internet of Things Journal.

[13]  Giuseppe Aceto,et al.  DISTILLER: Encrypted traffic classification via multimodal multitask deep learning , 2021, J. Netw. Comput. Appl..

[14]  Dongsuk Yook,et al.  Multitask Learning of Deep Neural Network-Based Keyword Spotting for IoT Devices , 2019, IEEE Transactions on Consumer Electronics.

[15]  Harshita Jha,et al.  Survey on various Scheduling Algorithms , 2017 .

[16]  M. Georgiopoulos,et al.  Feed-forward neural networks , 1994, IEEE Potentials.

[17]  Shyh-In Hwang,et al.  Combinatorial Optimization in Real-Time Scheduling: Theory and Algorithms , 2001, J. Comb. Optim..

[18]  Teruaki Hayashi,et al.  Feature Extraction of Laser Machining Data by Using Deep Multi-Task Learning , 2020, Inf..

[19]  Sebastian Ruder,et al.  An Overview of Multi-Task Learning in Deep Neural Networks , 2017, ArXiv.

[20]  Michael Freitag,et al.  Online-scheduling using past and real-time data. An assessment by discrete event simulation using exponential smoothing , 2017 .

[21]  Pierluigi Salvo Rossi,et al.  Bandwidth-Constrained Decentralized Detection of an Unknown Vector Signal via Multisensor Fusion , 2020, IEEE Transactions on Signal and Information Processing over Networks.

[22]  Shingo Yamaguchi,et al.  Physical Device Compatibility Support for Implementation of IoT Services with Design Once, Provide Anywhere Concept , 2021, Inf..