.png){kind=icon}
.png){kind=icon}
Return
Machine learning-driven routing optimization for energy-efficient 6G-enabled wireless sensor networks
.png){kind=icon}
PRE
AI
DOI：10.1016/j.aej.2025.07.032.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Future wireless networks under 6G will implement expansive Wireless Sensor Network (WSN) deployments that require extremely low latency and highly reliable and power-efficient systems. The networks encounter crucial impediments in routing protocol optimization that require network lifetime extension combined with demanding QoS standard fulfillment. The deployment of sensor systems requires energy-aware routing as its core element to achieve sustainable operation and maximal scalability. The routing methods from the past show their limitations by handling dynamic network maps poorly, alongside fluctuating power consumption. ML technology demonstrates successful performance in building complex network system models that optimize energy management through dynamic routing operations. In 6G-enabled WSNs, ML-based routing implements data-driven decision-making platforms to determine numerous routing paths using real-time energy information combined with traffic patterns and node mobility parameters to prolong network lifetime as well as improve packet delivery ratios and throughput, and latency under diverse conditions. This paper develops an advanced routing optimization system based on machine learning algorithms for WSNs utilizing 6G infrastructure. The system joins supervised learning technological methods and reinforcement approaches to perform automated energy parameter evaluations and adaptive forwarding strategy selection processes. The proposed framework receives evaluation based on conventional technologies through simulations using real energy models and wireless communication parameters. Performance metrics involving network lifetime, energy consumption together with delivery ratio are analyzed for different network topologies and sizes through quantitative evaluation. Energy efficiency, together with data reliability, experienced substantial improvements according to the study findings. This proposed work brings forward a multi-objective optimization methodology that handles performance trade-offs among delivery delays and path reliability, and energy allocation in networks. It demonstrates superior performance compared to existing models when used for sustainable routing design of 6G-integrated WSNs.
Keywords:
Wireless Sensor Networks (WSNs)
Machine learning
6G networks
Energy efficiency
Routing optimization
Reinforcement learning
Network lifetime
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.8
Papers:
6.3K
Citations:
2.6W
View more organizations