Multi-Objective Resource Scheduling for IoT Systems Using Reinforcement Learning

IoT embedded systems have multiple objectives that need to be maximized simultaneously. These objectives conflict with each other due to limited resources and tradeoffs that need to be made. This requires multi-objective optimization (MOO) and multiple Pareto-optimal solutions are possible. In such...

Full description

Saved in:
Bibliographic Details
Published in:Journal of low power electronics and applications 2022-12, Vol.12 (4), p.53
Main Authors: Shresthamali, Shaswot, Kondo, Masaaki, Nakamura, Hiroshi
Format: Article
Language:English
Subjects:
Algorithms
Analysis
Data compression
Electric power production
Embedded systems
Energy budget
Energy consumption
Energy harvesting
Internet of Things
Linear programming
Machine learning
Markov processes
multi objective optimization
multi-objective reinforcement learning
Multiple objective analysis
Optimization
Pareto optimization
Policies
Preferences
Resource scheduling
Sensors
Tradeoffs
Wireless sensor networks
wireless sensors
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:IoT embedded systems have multiple objectives that need to be maximized simultaneously. These objectives conflict with each other due to limited resources and tradeoffs that need to be made. This requires multi-objective optimization (MOO) and multiple Pareto-optimal solutions are possible. In such a case, tradeoffs are made w.r.t. a user-defined preference. This work presents a general Multi-objective Reinforcement Learning (MORL) framework for MOO of IoT embedded systems. This framework comprises a general Multi-objective Markov Decision Process (MOMDP) formulation and two novel low-compute MORL algorithms. The algorithms learn policies to tradeoff between multiple objectives using a single preference parameter. We take the energy scheduling problem in general Energy Harvesting Wireless Sensor Nodes (EHWSNs) as a case example in which a sensor node is required to maximize its sensing rate, and transmission performance as well as ensure long-term uninterrupted operation within a very tight energy budget. We simulate single-task and dual-task EHWSN systems to evaluate our framework. The results demonstrate that our MORL algorithms can learn better policies at lower learning costs and successfully tradeoff between multiple objectives at runtime.
ISSN:2079-9268
2079-9268
DOI:10.3390/jlpea12040053