Q-Learning-Based Power Allocation for Secure Wireless Communication in UAV-Aided Relay Network
Unmanned aerial vehicle (UAV)-aided wireless relay networks are at risk of eavesdropping activities due to their open nature. In this paper, we study the security of a UAV-aided selective relaying wireless network in which <inline-formula> <tex-math notation="LaTeX">$N$ </te...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9360739/ |
| _version_ | 1826938438302040064 |
|---|---|
| author | Sidqy I. Alnagar Anas M. Salhab Salam A. Zummo |
| author_facet | Sidqy I. Alnagar Anas M. Salhab Salam A. Zummo |
| author_sort | Sidqy I. Alnagar |
| collection | DOAJ |
| description | Unmanned aerial vehicle (UAV)-aided wireless relay networks are at risk of eavesdropping activities due to their open nature. In this paper, we study the security of a UAV-aided selective relaying wireless network in which <inline-formula> <tex-math notation="LaTeX">$N$ </tex-math></inline-formula> UAVs are employed as decode-and-forward (DF) relays linking a ground base station (BS) with <inline-formula> <tex-math notation="LaTeX">$L$ </tex-math></inline-formula> legitimate users on the ground in the presence of a passive eavesdropper (<inline-formula> <tex-math notation="LaTeX">$Eave$ </tex-math></inline-formula>). Direct links between the ground BS and both the ground users and the eavesdropper are assumed to be blocked. The ground-to-air and air-to-ground channels are assumed to follow Rician fading model with opportunistic scheduling scheme for UAVs and users selection. In order to secure data transmissions against such an interception action, the UAV of the worst UAV-selected user link transmits a jamming artificial noise (AN) signal to degrade <inline-formula> <tex-math notation="LaTeX">$Eave$ </tex-math></inline-formula> ability in decoding the confidential information successfully. The transmission outage probability, intercept probability, and hybrid outage probability are derived and analyzed. Due to the heavy computation burden raised by increasing the number of UAVs and users as well as the difficulty in estimating the instantaneous channel state information (CSI), existing traditional optimization methods are not highly efficient in solving the considered power allocation problem. Therefore, we propose a dynamic power control scheme based on Q-learning algorithm combined with statistical CSI where the hybrid outage probability is minimized. Simulation results show that the proposed algorithm efficiently reduces the hybrid outage probability with a noticeable reduction in the computational time. |
| first_indexed | 2024-12-22T22:21:16Z |
| format | Article |
| id | doaj.art-2dbd6aae748a4127a32fb6cb92d05333 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2025-02-17T18:57:57Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2dbd6aae748a4127a32fb6cb92d053332024-12-11T00:02:09ZengIEEEIEEE Access2169-35362021-01-019331693318010.1109/ACCESS.2021.30614069360739Q-Learning-Based Power Allocation for Secure Wireless Communication in UAV-Aided Relay NetworkSidqy I. Alnagar0https://orcid.org/0000-0002-1234-8464Anas M. Salhab1https://orcid.org/0000-0002-6777-0718Salam A. Zummo2https://orcid.org/0000-0002-8517-0724Department of Electrical Engineering, King Fahd University of Petroleum and Minerals, Dhahran, Saudi ArabiaDepartment of Electrical Engineering, King Fahd University of Petroleum and Minerals, Dhahran, Saudi ArabiaDepartment of Electrical Engineering, King Fahd University of Petroleum and Minerals, Dhahran, Saudi ArabiaUnmanned aerial vehicle (UAV)-aided wireless relay networks are at risk of eavesdropping activities due to their open nature. In this paper, we study the security of a UAV-aided selective relaying wireless network in which <inline-formula> <tex-math notation="LaTeX">$N$ </tex-math></inline-formula> UAVs are employed as decode-and-forward (DF) relays linking a ground base station (BS) with <inline-formula> <tex-math notation="LaTeX">$L$ </tex-math></inline-formula> legitimate users on the ground in the presence of a passive eavesdropper (<inline-formula> <tex-math notation="LaTeX">$Eave$ </tex-math></inline-formula>). Direct links between the ground BS and both the ground users and the eavesdropper are assumed to be blocked. The ground-to-air and air-to-ground channels are assumed to follow Rician fading model with opportunistic scheduling scheme for UAVs and users selection. In order to secure data transmissions against such an interception action, the UAV of the worst UAV-selected user link transmits a jamming artificial noise (AN) signal to degrade <inline-formula> <tex-math notation="LaTeX">$Eave$ </tex-math></inline-formula> ability in decoding the confidential information successfully. The transmission outage probability, intercept probability, and hybrid outage probability are derived and analyzed. Due to the heavy computation burden raised by increasing the number of UAVs and users as well as the difficulty in estimating the instantaneous channel state information (CSI), existing traditional optimization methods are not highly efficient in solving the considered power allocation problem. Therefore, we propose a dynamic power control scheme based on Q-learning algorithm combined with statistical CSI where the hybrid outage probability is minimized. Simulation results show that the proposed algorithm efficiently reduces the hybrid outage probability with a noticeable reduction in the computational time.https://ieeexplore.ieee.org/document/9360739/Unmanned aerial vehicleRician fadingphysical layer securityoutage probabilityintercept probabilityreinforcement learning |
| spellingShingle | Sidqy I. Alnagar Anas M. Salhab Salam A. Zummo Q-Learning-Based Power Allocation for Secure Wireless Communication in UAV-Aided Relay Network IEEE Access Unmanned aerial vehicle Rician fading physical layer security outage probability intercept probability reinforcement learning |
| title | Q-Learning-Based Power Allocation for Secure Wireless Communication in UAV-Aided Relay Network |
| title_full | Q-Learning-Based Power Allocation for Secure Wireless Communication in UAV-Aided Relay Network |
| title_fullStr | Q-Learning-Based Power Allocation for Secure Wireless Communication in UAV-Aided Relay Network |
| title_full_unstemmed | Q-Learning-Based Power Allocation for Secure Wireless Communication in UAV-Aided Relay Network |
| title_short | Q-Learning-Based Power Allocation for Secure Wireless Communication in UAV-Aided Relay Network |
| title_sort | q learning based power allocation for secure wireless communication in uav aided relay network |
| topic | Unmanned aerial vehicle Rician fading physical layer security outage probability intercept probability reinforcement learning |
| url | https://ieeexplore.ieee.org/document/9360739/ |
| work_keys_str_mv | AT sidqyialnagar qlearningbasedpowerallocationforsecurewirelesscommunicationinuavaidedrelaynetwork AT anasmsalhab qlearningbasedpowerallocationforsecurewirelesscommunicationinuavaidedrelaynetwork AT salamazummo qlearningbasedpowerallocationforsecurewirelesscommunicationinuavaidedrelaynetwork |