Reinforcement Learning in Dynamic Task Scheduling: A Review
- PDF / 1,832,082 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 79 Downloads / 239 Views
REVIEW ARTICLE
Reinforcement Learning in Dynamic Task Scheduling: A Review Chathurangi Shyalika1 · Thushari Silva1 · Asoka Karunananda1 Received: 12 July 2020 / Accepted: 8 September 2020 © Springer Nature Singapore Pte Ltd 2020
Abstract Scheduling is assigning shared resources over time to efficiently complete the tasks over a given period of time. The term is applied separately for tasks and resources correspondingly in task scheduling and resource allocation. Scheduling is a popular topic in operational management and computer science. Effective schedules ensure system efficiency, effective decision making, minimize resource wastage and cost, and enhance overall productivity. It is generally a tedious task to choose the most accurate resources in performing work items and schedules in both computing and business process execution. Especially in real-world dynamic systems where multiple agents involve in scheduling various dynamic tasks is a challenging issue. Reinforcement Learning is an emergent technology which has been able to solve the problem of the optimal task and resource scheduling dynamically. This review paper is about a research study that focused on Reinforcement Learning techniques that have been used for dynamic task scheduling. The paper addresses the results of the study by means of the state-of-theart on Reinforcement learning techniques used in dynamic task scheduling and a comparative review of those techniques. Keywords Task scheduling · Reinforcement learning · Multi-agent · Dynamic · Environment uncertainty
Introduction Task allocation ensures that the correct resources have been allocated effectively to perform work items/tasks of a particular consequence at the right time. It guarantees the balance between the demand for process execution facilities against the availability of these resources. The allocation of tasks or resources, also known as scheduling, is applicable to a number of applications, such as Industrial Workforce Management, Grid Computing, Public Transport and Network Routing. Dynamic task scheduling has gained significant attention in these fields as it is crucial for effective resource sharing. Scheduling in a computer system is done by the component named Scheduler, which mainly concerns throughput, * Chathurangi Shyalika [email protected] Thushari Silva [email protected] Asoka Karunananda [email protected] 1
Department of Computational Mathematics, Faculty of Information Technology, University of Moratuwa, Katubedda, Sri Lanka
latency and response time. Throughput refers to how fast it could finish a certain number of tasks from beginning to end per unit of time. In contrast, latency is the turnaround time or the time it takes to complete the job from the time of request or submission until the finish, that includes the waiting time before it could be served. Response time is the time it has taken for the process or request to be served, in short, the waiting time. Job-Shop Scheduling Problem (JSSP) [1–4] is a common problem of optimization in th
Data Loading...
