Accelerated evolution: A biologically-inspired approach for augmenting self-star properties in wireless sensor networks
Wireless sensor networks (WSNs) possess inherent tradeoffs among conflicting performance objectives such as data yield, data fidelity and power consumption. In order to address this challenge, this paper proposes a biologically-inspired application framework for WSNs. The proposed framework, called...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Book Series |
| Published: |
2018
|
| Subjects: | |
| Online Access: | https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84857565232&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/51537 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Chiang Mai University |
| Summary: | Wireless sensor networks (WSNs) possess inherent tradeoffs among conflicting performance objectives such as data yield, data fidelity and power consumption. In order to address this challenge, this paper proposes a biologically-inspired application framework for WSNs. The proposed framework, called El Niño, models an application as a decentralized group of software agents. This is analogous to a bee colony (application) consisting of bees (agents). Agents collect sensor data on individual nodes and carry the data to base stations. They perform this data collection functionality by autonomously sensing their local network conditions and adaptively invoking biological behaviors such as pheromone emission, swarming, reproduction and migration. Each agent carries its own operational parameters, as genes, which govern its behavior invocation and configure its underlying sensor nodes. El Niño allows agents to evolve and adapt their operational parameters to network dynamics and disruptions by seeking the optimal tradeoffs among conflicting performance objectives. This evolution process is augmented by a notion of accelerated evolution. It allows agents to evolve their operational parameters by learning dynamic network conditions in the network and approximating their performance under the conditions. This is intended to expedite agent evolution to adapt to network dynamics and disruptions. © 2012 Springer-Verlag Berlin Heidelberg. |
|---|