Dynamic Power Management of Energy Harvesting Wireless Sensor Node using Fuzzy Q-learning
| Autor: | 林梓豪 |
|---|---|
| Rok vydání: | 2018 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 106 In energy harvesting wireless sensor node, how to balance energy production and consumption through dynamic energy management such that the goal of sustainable operation can be achieved is one of the most important research topics. In this study, a fuzzy Q-learning based dynamic power management of the wireless sensor node is proposed. The proposed method applies the fuzzy inference system for the energy management of energy harvest wireless sensor node and uses Q-learning to train, evaluate, and update the fuzzy rule base. Through the interaction with the environment, the learning agent of the fuzzy Q-Learning will be able to find the appropriate fuzzy rules and adjust the duty cycle under the goal of energy neutrality so that the sustainable operation of the wireless sensor node can be achieved. Experimental results show that the fuzzy Q-learning based dynamic power management can maintain a higher battery charge status than other existed methods and achieve the sustainable operation of the wireless sensor node. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|