Related Experiment Video
Updated: Mar 13, 2026
05:30
Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
Published on: September 8, 2023
1.2K
Energy optimized scheduling in wireless sensor networks (WSNs) using hybrid bio-inspired reinforcement learning
M Vergin Raja Sarobin1, S Akil2, S Berin Shalu2
1School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, Tamil Nadu, 600127, India. verginraja.m@vit.ac.in.
Scientific Reports
|March 12, 2026
Summary
A new RL-HAPSO method optimizes Wireless Sensor Network (WSN) scheduling for Internet of Things (IoT) by combining Ant Colony Optimization, Particle Swarm Optimization, and Reinforcement Learning. This approach enhances energy efficiency, fault tolerance, and coverage in smart infrastructure.
Area of Science:
- Computer Science
- Electrical Engineering
- Network Engineering
Background:
- Smart infrastructure management benefits from real-time environmental tracking and cyber-physical data processing.
- Wireless Sensor Networks (WSNs) integrated with the Internet of Things (IoT) are crucial for these advancements.
- WSN scheduling faces challenges due to limited energy, hostile environments, and dynamic topologies, with existing algorithms like Simulated Annealing and Artificial Bee Colony showing suboptimal performance.
Purpose of the Study:
- To introduce RL-HAPSO, a novel hybrid method for optimizing WSN scheduling.
- To address limitations of traditional algorithms in energy-constrained and dynamic WSN environments.
- To improve energy efficiency, coverage, fault tolerance, and adaptability in WSN scheduling.
Main Methods:
- The RL-HAPSO method integrates Ant Colony Optimization (ACO) for energy-efficient node selection.
- Particle Swarm Optimization (PSO) is employed to enhance coverage and minimize redundancy.
- Q-learning Reinforcement Learning (RL) dynamically selects activation schedules based on real-time network states.
Main Results:
- RL-HAPSO demonstrated superior optimization costs, achieving enhanced fault tolerance, coverage, and minimal energy usage compared to individual algorithms and a non-RL hybrid model.
- The system exhibited robust behavior and automatic adjustments during performance alterations, including node failures and environmental variations.
- Execution times were in the microsecond interval, indicating efficient processing.
Conclusions:
- The proposed RL-HAPSO methodology offers a viable and robust approach for resource-aware and smart WSN scheduling in future IoT applications.
- The adaptive capability of RL-HAPSO ensures consistent performance even under challenging network conditions.
- This hybrid approach effectively balances energy efficiency, network coverage, and operational reliability.
