Dynamic process scheduling and resource allocation in distributed environment: an agent-based modelling and simulation |
| |
Authors: | Poulami Dalapati Piyush Agarwal Animesh Dutta Swapan Bhattacharya |
| |
Affiliation: | 1. Department of CSE, National Institute of Technology Durgapur, Durgapur, India;2. Arcesium India Private Limited, Hyderabad, India;3. Department of CSE, Jadavpur University, Kolkata, India |
| |
Abstract: | This paper addresses the issues concerning resource allocation and process scheduling in a dynamic environment, where resources are distributed and availability of them is uncertain. In this context, we introduce a new multi-agent-based resource allocation and process scheduling approach, where agents communicate and cooperate among themselves to produce an optimal schedule. A distributed constraint optimization problem-based model in accordance with Markov Decision Process is proposed in this regard. We overcome the hardship of existing centralized approach and our technique optimizes not only the process completion delay but also the number of resources being idle, which is much more beneficial. Apart from the theoretical approach, we take a case study in its practical application domain to validate our claim. Analysis and experimental results show that this proposed method outperforms the state-of-the-art methods and bridges the gap between theory and its applications. |
| |
Keywords: | Multi-agent systems resource allocation process scheduling distributed constraint optimization agent-based modelling |
|
|