Security Enhancement for Deep Reinforcement Learning-Based Strategy in Energy-Efficient Wireless Sensor Networks
Abstract
:1. Introduction
- We propose a novel DeppNR strategy that intelligently optimizes energy consumption in WSNs, significantly extending network lifecycles beyond current benchmarks.
- The proposed DeepNR strategy introduces cutting-edge security enhancements directly embedded within the DRL model, offering robust protection against a wide array of cyber threats, thereby elevating the network’s resilience.
- The experiments verify the effectiveness and superiority of the proposed DeepNR. Compared with other conventional methods, DeepNR can significantly improve the energy efficiency of WSN while ensuring security.
2. Related Work
2.1. Traditional Solutions
2.2. Machine Learning-Based Solutions
2.3. Existing Challenges and Gaps
- Energy Efficiency. Given the limited power resources of sensor nodes, extending network lifespan while maintaining operational effectiveness remains a primary concern.
- Security. The open nature of wireless communication exposes WSNs to a range of security threats, from data breaches to node tampering, necessitating comprehensive security solutions.
- Adaptability. Dynamic network conditions and evolving threat landscapes require adaptable strategies that traditional static methods cannot provide.
3. Proposed Method
3.1. Network Design
- Customization for WSNs. We have designed the DNN architecture specifically to handle the high-dimensional state space characteristic of WSNs, which is not addressed by standard DNN applications.
- Real-time adaptation. The combination of DNNs with DRL enables our strategy to learn and adapt in real time to changing network conditions and attack patterns, a critical requirement for WSNs that is not commonly met by traditional DNN applications.
- Multi-level decision-making. Our approach uses a DNN-based policy to perform multi-level decision-making, dynamically adjusting network strategies to balance energy efficiency with robust security measures.
- Composite reward function. We introduce a new composite reward function within the DRL framework to guide the training process of the DNN, which is specifically designed to address the dual objectives of energy efficiency and security in WSNs.
3.2. Strategy Optimization
- Enhanced state space representation. The state space in DeepNR has been designed to encapsulate a more comprehensive set of network parameters, which are specifically chosen to represent the complex dynamics of WSNs.
- Customized reward function. We employ a customized reward function that is particularly formulated to address the dual objectives of maximizing energy efficiency and ensuring network security, which is not traditionally the focus of standard deep Q-learning applications.
- Policy optimization for WSNs. Our approach adapts the policy optimization process to suit the specific operational constraints and performance goals of WSNs, such as node energy limitations and the need for rapid response to security threats.
- Advanced experience replay mechanism. We have implemented an advanced experience replay mechanism that better suits the temporal and spatial variability in WSNs, enhancing the learning process beyond the typical deep Q-learning approach.
- Integration with WSN-specific protocols. DeepNR is integrated with WSN-specific protocols, which enable a seamless transition from learned strategies to actionable policies in a real-world network environment.
4. Experiment and Evaluation
4.1. Network Life Cycle
4.2. Data Throughput
4.3. Security Assessment
4.4. Energy Distribution and Balance
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Zhu, H.; Huang, Z.; Lam, C.T.; Wu, Q.; Yang, B.; Ng, B.K. A Space Shift Keying-Based Optimization Scheme for Secure Communication in IIoT. IEEE Syst. J. 2023, 17, 5261–5271. [Google Scholar] [CrossRef]
- Al Hayani, B.; Ilhan, H. Image transmission over decode and forward based cooperative wireless multimedia sensor networks for Rayleigh fading channels in medical internet of things (MIoT) for remote health-care and health communication monitoring. J. Med. Imaging Health Inform. 2020, 10, 160–168. [Google Scholar] [CrossRef]
- Akyildiz, I.F.; Su, W.; Sankarasubramaniam, Y.; Cayirci, E. Wireless sensor networks: A survey. Comput. Netw. 2002, 38, 393–422. [Google Scholar] [CrossRef]
- Wang, X.; Liu, X.; Cheng, C.T.; Deng, L.; Chen, X.; Xiao, F. A joint user scheduling and trajectory planning data collection strategy for the UAV-assisted WSN. IEEE Commun. Lett. 2021, 25, 2333–2337. [Google Scholar] [CrossRef]
- Kim, J.; Lee, D.; Hwang, J.; Hong, S.; Shin, D.; Shin, D. Wireless sensor network (WSN) configuration method to increase node energy efficiency through clustering and location information. Symmetry 2021, 13, 390. [Google Scholar] [CrossRef]
- Tripathy, B.K.; Jena, S.K.; Reddy, V.; Das, S.; Panda, S.K. A novel communication framework between MANET and WSN in IoT based smart environment. Int. J. Inf. Technol. 2021, 13, 921–931. [Google Scholar] [CrossRef]
- Devi, V.S.; Ravi, T.; Priya, S.B. Cluster based data aggregation scheme for latency and packet loss reduction in WSN. Comput. Commun. 2020, 149, 36–43. [Google Scholar] [CrossRef]
- Donta, P.K.; Amgoth, T.; Annavarapu, C.S.R. Delay-aware data fusion in duty-cycled wireless sensor networks: A Q-learning approach. Sustain. Comput. Inform. Syst. 2022, 33, 100642. [Google Scholar] [CrossRef]
- Daanoune, I.; Abdennaceur, B.; Ballouk, A. A comprehensive survey on LEACH-based clustering routing protocols in Wireless Sensor Networks. Ad Hoc Netw. 2021, 114, 102409. [Google Scholar] [CrossRef]
- Khedr, A.M.; Aziz, A.; Osamy, W. Successors of PEGASIS protocol: A comprehensive survey. Comput. Sci. Rev. 2021, 39, 100368. [Google Scholar] [CrossRef]
- Ahmad, R.; Wazirali, R.; Abu-Ain, T. Machine learning for wireless sensor networks security: An overview of challenges and issues. Sensors 2022, 22, 4730. [Google Scholar] [CrossRef] [PubMed]
- Zhu, H.; Peng, Y.; Xu, H.; Tong, F.; Jiang, X.Q.; Mirza, M.M. Secrecy enhancement for SSK-based communications in wireless sensing systems. IEEE Sens. J. 2022, 22, 18192–18201. [Google Scholar] [CrossRef]
- Dalal, B.; Kukarni, S. Wireless sensor networks: Applications. In Wireless Sensor Networks: Design, Deployment and Applications; BoD–Books on Demand: Norderstedt, Germany, 2021; p. 3. [Google Scholar]
- Jiang, W. Graph-based deep learning for communication networks: A survey. Comput. Commun. 2022, 185, 40–54. [Google Scholar] [CrossRef]
- Jiang, K.; Zhou, H.; Zeng, D.; Wu, J. Multi-agent reinforcement learning for cooperative edge caching in internet of vehicles. In Proceedings of the 2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS), Delhi, India, 10–13 December 2020; pp. 455–463. [Google Scholar]
- Arulkumaran, K.; Deisenroth, M.P.; Brundage, M.; Bharath, A.A. Deep reinforcement learning: A brief survey. IEEE Signal Process. Mag. 2017, 34, 26–38. [Google Scholar] [CrossRef]
- Perrig, A.; Szewczyk, R.; Wen, V.; Culler, D.; Tygar, J. SPINS: Security protocols for sensor networks. In Proceedings of the 7th Annual International Conference on Mobile Computing and Networking, Rome, Italy, 16–21 July 2001; pp. 189–199. [Google Scholar]
- Seo, J.B. On minimizing energy consumption of duty-cycled wireless sensors. IEEE Commun. Lett. 2015, 19, 1698–1701. [Google Scholar] [CrossRef]
- Akoglu, L.; Tong, H.; Koutra, D. Graph based anomaly detection and description: A survey. Data Min. Knowl. Discov. 2015, 29, 626–688. [Google Scholar] [CrossRef]
- Ioannou, C.; Vassiliou, V.; Sergiou, C. An intrusion detection system for wireless sensor networks. In Proceedings of the 2017 24th International Conference on Telecommunications (ICT), Limassol, Cyprus, 3–5 May 2017; pp. 1–5. [Google Scholar]
- Li, G.; Hari, S.K.S.; Sullivan, M.; Tsai, T.; Pattabiraman, K.; Emer, J.; Keckler, S.W. Understanding error propagation in deep learning neural network (DNN) accelerators and applications. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, Denver, CO, USA, 12–17 November 2017; pp. 1–12. [Google Scholar]
- Janarthanan, A.; Srinivasan, V. Multi-objective cluster head-based energy aware routing using optimized auto-metric graph neural network for secured data aggregation in Wireless Sensor Network. Int. J. Commun. Syst. 2024, 37, e5664. [Google Scholar] [CrossRef]
- Sivakumar, N.R.; Nagarajan, S.M.; Devarajan, G.G.; Pullagura, L.; Mahapatra, R.P. Enhancing network lifespan in wireless sensor networks using deep learning based Graph Neural Network. Phys. Commun. 2023, 59, 102076. [Google Scholar] [CrossRef]
- Hameed, S.S.; Abdulshaheed, H.R.; Ali, Z.L.; Gheni, H.M. Implement DNN technology by using wireless sensor network system based on IOT applications. Period. Eng. Nat. Sci. 2022, 10, 128–137. [Google Scholar] [CrossRef]
- Bhaskar, K.V.; Kumanan, T.; Southry, S.S.; Elangovan, V. Deep Neural Network Algorithm to Improve Link Reliability in Wireless Sensor Networks. In Proceedings of the 2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India, 6–8 July 2023; pp. 476–480. [Google Scholar]
- Li, Y.; Hu, X.; Zhuang, Y.; Gao, Z.; Zhang, P.; El-Sheimy, N. Deep reinforcement learning (DRL): Another perspective for unsupervised wireless localization. IEEE Internet Things J. 2019, 7, 6279–6287. [Google Scholar] [CrossRef]
- Kaelbling, L.P.; Littman, M.L.; Moore, A.W. Reinforcement learning: A survey. J. Artif. Intell. Res. 1996, 4, 237–285. [Google Scholar] [CrossRef]
- Zhou, H.; Jiang, K.; He, S.; Min, G.; Wu, J. Distributed Deep Multi-Agent Reinforcement Learning for Cooperative Edge Caching in Internet-of-Vehicles. IEEE Trans. Wirel. Commun. 2023, 22, 9595–9609. [Google Scholar] [CrossRef]
- Wachi, A.; Sui, Y. Safe reinforcement learning in constrained Markov decision processes. In Proceedings of the International Conference on Machine Learning, PMLR, Virtual Event, 13–18 July 2020; pp. 9797–9806. [Google Scholar]
- Goswami, P.; Mukherjee, A.; Hazra, R.; Yang, L.; Ghosh, U.; Qi, Y.; Wang, H. AI based energy efficient routing protocol for intelligent transportation system. IEEE Trans. Intell. Transp. Syst. 2021, 23, 1670–1679. [Google Scholar] [CrossRef]
- Zhao, B.; Zhao, X. Deep reinforcement learning resource allocation in wireless sensor networks with energy harvesting and relay. IEEE Internet Things J. 2021, 9, 2330–2345. [Google Scholar] [CrossRef]
- Amer, A.; Abd El-Samie, F.E.; Salem, A.A.; Shokair, M.; Benaya, A. Secure transmission in wireless sensor networks via reconfigurable intelligent surface. Digit. Signal Process. 2023, 140, 104083. [Google Scholar] [CrossRef]
- Watkins, C.J.; Dayan, P. Q-learning. Mach. Learn. 1992, 8, 279–292. [Google Scholar] [CrossRef]
- Dubey, G.P.; Stalin, S.; Alqahtani, O.; Alasiry, A.; Sharma, M.; Aleryani, A.; Shukla, P.K.; Alouane, M.T.H. Optimal path selection using reinforcement learning based ant colony optimization algorithm in IoT-Based wireless sensor networks with 5G technology. Comput. Commun. 2023, 212, 377–389. [Google Scholar] [CrossRef]
- Yadav, L.; Sunitha, C. Low energy adaptive clustering hierarchy in wireless sensor network (LEACH). Int. J. Comput. Sci. Inf. Technol. 2014, 5, 4661–4664. [Google Scholar]
- Mahakud, R.; Rath, S.; Samantaray, M.; Sinha, B.; Priya, P.; Nayak, A.; Kumari, A. Energy management in wireless sensor network using PEGASIS. Procedia Comput. Sci. 2016, 92, 207–212. [Google Scholar] [CrossRef]
- Poluru, R.K.; Reddy, M.; Basha, S.M.; Patan, R.; Kallam, S. Enhanced adaptive distributed energy-efficient clustering (EADEEC) for wireless sensor networks. Recent Adv. Comput. Sci. Commun. (Former. Recent Patents Comput. Sci.) 2020, 13, 168–172. [Google Scholar] [CrossRef]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Hu, L.; Han, C.; Wang, X.; Zhu, H.; Ouyang, J. Security Enhancement for Deep Reinforcement Learning-Based Strategy in Energy-Efficient Wireless Sensor Networks. Sensors 2024, 24, 1993. https://doi.org/10.3390/s24061993
Hu L, Han C, Wang X, Zhu H, Ouyang J. Security Enhancement for Deep Reinforcement Learning-Based Strategy in Energy-Efficient Wireless Sensor Networks. Sensors. 2024; 24(6):1993. https://doi.org/10.3390/s24061993
Chicago/Turabian StyleHu, Liyazhou, Chao Han, Xiaojun Wang, Han Zhu, and Jian Ouyang. 2024. "Security Enhancement for Deep Reinforcement Learning-Based Strategy in Energy-Efficient Wireless Sensor Networks" Sensors 24, no. 6: 1993. https://doi.org/10.3390/s24061993
APA StyleHu, L., Han, C., Wang, X., Zhu, H., & Ouyang, J. (2024). Security Enhancement for Deep Reinforcement Learning-Based Strategy in Energy-Efficient Wireless Sensor Networks. Sensors, 24(6), 1993. https://doi.org/10.3390/s24061993