Collaborative duty cycling strategies in energy harvesting sensor networks
Computer-Aided Civil and Infrastructure Engineering Energy harvesting wireless sensor networks are a promising solution for low cost, long lasting civil monitoring applications. But management of energy consumption is a critical concern to ensure these systems provide maximal utility. Many common c...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020
|
| Online Access: | https://hdl.handle.net/1721.1/126602 |
| _version_ | 1826189820997664768 |
|---|---|
| author | Long, James Buyukozturk, Oral |
| author2 | Massachusetts Institute of Technology. Department of Civil and Environmental Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Civil and Environmental Engineering Long, James Buyukozturk, Oral |
| author_sort | Long, James |
| collection | MIT |
| description | Computer-Aided Civil and Infrastructure Engineering Energy harvesting wireless sensor networks are a promising solution for low cost, long lasting civil monitoring applications. But management of energy consumption is a critical concern to ensure these systems provide maximal utility. Many common civil applications of these networks are fundamentally concerned with detecting and analyzing infrequently occurring events. To conserve energy in these situations, a subset of nodes in the network can assume active duty, listening for events of interest, while the remaining nodes enter low power sleep mode to conserve battery. However, judicious planning of the sequence of active node assignments is needed to ensure that as many nodes as possible can be reached upon the detection of an event, and that the system maintains capability in times of low energy harvesting capabilities. In this article, we propose a novel reinforcement learning (RL) agent, which acts as a centralized power manager for this system. We develop a comprehensive simulation environment to emulate the behavior of an energy harvesting sensor network, with consideration of spatially varying energy harvesting capabilities, and wireless connectivity. We then train the proposed RL agent to learn optimal node selection strategies through interaction with the simulation environment. The behavior and performance of these strategies are tested on real unseen solar energy data, to demonstrate the efficacy of the method. The deep RL agent is shown to outperform baseline approaches on both seen and unseen data. |
| first_indexed | 2024-09-23T08:23:23Z |
| format | Article |
| id | mit-1721.1/126602 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T08:23:23Z |
| publishDate | 2020 |
| publisher | Wiley |
| record_format | dspace |
| spelling | mit-1721.1/1266022022-09-23T12:35:37Z Collaborative duty cycling strategies in energy harvesting sensor networks Long, James Buyukozturk, Oral Massachusetts Institute of Technology. Department of Civil and Environmental Engineering Computer-Aided Civil and Infrastructure Engineering Energy harvesting wireless sensor networks are a promising solution for low cost, long lasting civil monitoring applications. But management of energy consumption is a critical concern to ensure these systems provide maximal utility. Many common civil applications of these networks are fundamentally concerned with detecting and analyzing infrequently occurring events. To conserve energy in these situations, a subset of nodes in the network can assume active duty, listening for events of interest, while the remaining nodes enter low power sleep mode to conserve battery. However, judicious planning of the sequence of active node assignments is needed to ensure that as many nodes as possible can be reached upon the detection of an event, and that the system maintains capability in times of low energy harvesting capabilities. In this article, we propose a novel reinforcement learning (RL) agent, which acts as a centralized power manager for this system. We develop a comprehensive simulation environment to emulate the behavior of an energy harvesting sensor network, with consideration of spatially varying energy harvesting capabilities, and wireless connectivity. We then train the proposed RL agent to learn optimal node selection strategies through interaction with the simulation environment. The behavior and performance of these strategies are tested on real unseen solar energy data, to demonstrate the efficacy of the method. The deep RL agent is shown to outperform baseline approaches on both seen and unseen data. 2020-08-14T22:43:39Z 2020-08-14T22:43:39Z 2019-12 2020-08-14T12:25:47Z Article http://purl.org/eprint/type/JournalArticle 1093-9687 1467-8667 https://hdl.handle.net/1721.1/126602 Long, James and Oral Buyukozturk. "Collaborative duty cycling strategies in energy harvesting sensor networks." Computer-Aided Civil and Infrastructure Engineering 35, 6 (December 2019): 534-548 © 2019 Wiley en http://dx.doi.org/10.1111/mice.12522 Computer-Aided Civil and Infrastructure Engineering Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Wiley Prof. Buyukozturk via Elizabeth Soergel |
| spellingShingle | Long, James Buyukozturk, Oral Collaborative duty cycling strategies in energy harvesting sensor networks |
| title | Collaborative duty cycling strategies in energy harvesting sensor networks |
| title_full | Collaborative duty cycling strategies in energy harvesting sensor networks |
| title_fullStr | Collaborative duty cycling strategies in energy harvesting sensor networks |
| title_full_unstemmed | Collaborative duty cycling strategies in energy harvesting sensor networks |
| title_short | Collaborative duty cycling strategies in energy harvesting sensor networks |
| title_sort | collaborative duty cycling strategies in energy harvesting sensor networks |
| url | https://hdl.handle.net/1721.1/126602 |
| work_keys_str_mv | AT longjames collaborativedutycyclingstrategiesinenergyharvestingsensornetworks AT buyukozturkoral collaborativedutycyclingstrategiesinenergyharvestingsensornetworks |