Back to Search
Start Over
Joint Transaction Transmission and Channel Selection in Cognitive Radio Based Blockchain Networks: A Deep Reinforcement Learning Approach
- Source :
- ICASSP
- Publication Year :
- 2018
-
Abstract
- To ensure that the data aggregation, data storage, and data processing are all performed in a decentralized but trusted manner, we propose to use the blockchain with the mining pool to support IoT services based on cognitive radio networks. As such, the secondary user can send its sensing data, i.e., transactions, to the mining pools. After being verified by miners, the transactions are added to the blocks. However, under the dynamics of the primary channel and the uncertainty of the mempool state of the mining pool, it is challenging for the secondary user to determine an optimal transaction transmission policy. In this paper, we propose to use the deep reinforcement learning algorithm to derive an optimal transaction transmission policy for the secondary user. Specifically, we adopt a Double Deep-Q Network (DDQN) that allows the secondary user to learn the optimal policy. The simulation results clearly show that the proposed deep reinforcement learning algorithm outperforms the conventional Q-learning scheme in terms of reward and learning speed.
- Subjects :
- Primary channel
Networking and Internet Architecture (cs.NI)
FOS: Computer and information sciences
Blockchain
Computer science
business.industry
020206 networking & telecommunications
02 engineering and technology
Computer Science - Networking and Internet Architecture
Cognitive radio
Transmission (telecommunications)
0202 electrical engineering, electronic engineering, information engineering
Reinforcement learning
020201 artificial intelligence & image processing
business
Database transaction
Communication channel
Computer network
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Journal :
- ICASSP
- Accession number :
- edsair.doi.dedup.....1bf0576270175da1df1318873ac7cc44