Deep Reinforcement Learning-Based Multi-Hop State-Aware Routing Strategy for Wireless Sensor Networks
With the development of wireless sensor network technology, the routing strategy has important significance in the Internet of Things. An efficient routing strategy is one of the fundamental technologies to ensure the correct and fast transmission of wireless sensor networks. In this paper, we study...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/10/4436 |
| _version_ | 1797534273816756224 |
|---|---|
| author | Aiqi Zhang Meiyi Sun Jiaqi Wang Zhiyi Li Yanbo Cheng Cheng Wang |
| author_facet | Aiqi Zhang Meiyi Sun Jiaqi Wang Zhiyi Li Yanbo Cheng Cheng Wang |
| author_sort | Aiqi Zhang |
| collection | DOAJ |
| description | With the development of wireless sensor network technology, the routing strategy has important significance in the Internet of Things. An efficient routing strategy is one of the fundamental technologies to ensure the correct and fast transmission of wireless sensor networks. In this paper, we study how to combine deep learning technology with routing technology to propose an efficient routing strategy to cope with network topology changes. First, we use the recurrent neural network combined with the deep deterministic policy gradient method to predict the network traffic distribution. Second, the multi-hop node state is considered as the input of a double deep Q network. Therefore, the nodes can make routing decisions according to the current state of the network. Multi-hop state-aware routing strategy based on traffic flow forecasting (MHSA-TFF) is proposed. Simulation results show that the MHSA-TFF can improve transmission delay, average routing length, and energy efficiency. |
| first_indexed | 2024-03-10T11:27:16Z |
| format | Article |
| id | doaj.art-df9c0040a0d444159e6c5d10b40b0112 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T11:27:16Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-df9c0040a0d444159e6c5d10b40b01122023-11-21T19:34:34ZengMDPI AGApplied Sciences2076-34172021-05-011110443610.3390/app11104436Deep Reinforcement Learning-Based Multi-Hop State-Aware Routing Strategy for Wireless Sensor NetworksAiqi Zhang0Meiyi Sun1Jiaqi Wang2Zhiyi Li3Yanbo Cheng4Cheng Wang5School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaWith the development of wireless sensor network technology, the routing strategy has important significance in the Internet of Things. An efficient routing strategy is one of the fundamental technologies to ensure the correct and fast transmission of wireless sensor networks. In this paper, we study how to combine deep learning technology with routing technology to propose an efficient routing strategy to cope with network topology changes. First, we use the recurrent neural network combined with the deep deterministic policy gradient method to predict the network traffic distribution. Second, the multi-hop node state is considered as the input of a double deep Q network. Therefore, the nodes can make routing decisions according to the current state of the network. Multi-hop state-aware routing strategy based on traffic flow forecasting (MHSA-TFF) is proposed. Simulation results show that the MHSA-TFF can improve transmission delay, average routing length, and energy efficiency.https://www.mdpi.com/2076-3417/11/10/4436multi-hop state-awaretraffic flow predictiondeep reinforcement learningwireless sensor networks |
| spellingShingle | Aiqi Zhang Meiyi Sun Jiaqi Wang Zhiyi Li Yanbo Cheng Cheng Wang Deep Reinforcement Learning-Based Multi-Hop State-Aware Routing Strategy for Wireless Sensor Networks Applied Sciences multi-hop state-aware traffic flow prediction deep reinforcement learning wireless sensor networks |
| title | Deep Reinforcement Learning-Based Multi-Hop State-Aware Routing Strategy for Wireless Sensor Networks |
| title_full | Deep Reinforcement Learning-Based Multi-Hop State-Aware Routing Strategy for Wireless Sensor Networks |
| title_fullStr | Deep Reinforcement Learning-Based Multi-Hop State-Aware Routing Strategy for Wireless Sensor Networks |
| title_full_unstemmed | Deep Reinforcement Learning-Based Multi-Hop State-Aware Routing Strategy for Wireless Sensor Networks |
| title_short | Deep Reinforcement Learning-Based Multi-Hop State-Aware Routing Strategy for Wireless Sensor Networks |
| title_sort | deep reinforcement learning based multi hop state aware routing strategy for wireless sensor networks |
| topic | multi-hop state-aware traffic flow prediction deep reinforcement learning wireless sensor networks |
| url | https://www.mdpi.com/2076-3417/11/10/4436 |
| work_keys_str_mv | AT aiqizhang deepreinforcementlearningbasedmultihopstateawareroutingstrategyforwirelesssensornetworks AT meiyisun deepreinforcementlearningbasedmultihopstateawareroutingstrategyforwirelesssensornetworks AT jiaqiwang deepreinforcementlearningbasedmultihopstateawareroutingstrategyforwirelesssensornetworks AT zhiyili deepreinforcementlearningbasedmultihopstateawareroutingstrategyforwirelesssensornetworks AT yanbocheng deepreinforcementlearningbasedmultihopstateawareroutingstrategyforwirelesssensornetworks AT chengwang deepreinforcementlearningbasedmultihopstateawareroutingstrategyforwirelesssensornetworks |