.png){kind=icon}
.png){kind=icon}
Return
Charger Scheduling Optimization Framework
.png){kind=icon}
PRE
AI
DOI：10.1109/nca.2019.8935036.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Wireless Rechargeable Sensor Network (WRSN), consisting of sensors with rechargeable batteries and mobile chargers, has become a promising solution to the energy limitation problem in Wireless Sensor Networks (WSNs). Charger scheduling optimization focuses on optimizing the trajectory of mobile chargers to prolong the life of a WRSN system. Charger scheduling optimization problems are in general NP-hard. Previous solutions using traditional algorithms often require problem specific design and a trade-off between the performance and computing time. An insight into these optimization problems is that a domain-specific charger scheduling strategy could be learned automatically when the objective function of an optimization problem is considered as a reward. We model charger scheduling optimization problems using a weighted graph and consider the objective function as a cumulative reward of charging sensors along a charging path in one cycle. We then build a deep reinforcement learning based framework to solve a diverse range of charger scheduling optimization problems. The biggest advantage of the framework is that an optimal charger scheduling strategy can be learned from previous experiences, i.e., different graphs with various sizes. A framework also simplifies the complexity of algorithm design for individual charger scheduling optimization problem. We compare the performance of algorithms based on the proposed framework with traditional ones on a set of selected charger scheduling optimization problems. They outperform all existing algorithms.
Keywords:
Wireless rechargeable sensor networks
Mobile charger scheduling
Deep reinforcement learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
I
IF:
0
Papers:
8
Citations:
0