Intelligent Congestion Control in Wireless Sensor Networks (WSN) Based on Generative Adversarial Networks (GANs) and Optimization Algorithms
Abstract
:1. Introduction
- Congestion Control Framework: A multi-stage approach for detecting, notifying, and mitigating congestion in WSNs, addressing energy and traffic challenges.
- Energy-Efficient Routing: Utilizes GANs for realistic clustering and ACO for efficient CH selection to balance network load.
- Pheromone-Based Routing: Introduces a pheromone system for selecting low-congestion paths, improving data flow and reliability.
- Integrated QoS Metrics: Uses key QoS metrics (latency, throughput, reliability) to evaluate and enhance network performance under congestion.
2. Related Work
Comparative Outlook
3. Problem Statement
3.1. Strategies for Congestion Control in Wireless Sensor Networks
3.2. Energy Consumption Model
3.3. QoS Factors
3.4. Proposed Method
Algorithm 1: WSN Cluster-Based Routing with ACO algorithm |
1. for each node i in range (1, N): 2. deploy node i randomly within M×M area 3. set initial energy = 4. for each time t: 5. = - sum([i][j] for j in range (1, t)) 6. calculate distance for node i to BS 7. if < : 8. = * () ^ γ 9. end if 10. end for 11. while GAN has not converged: 12. generate synthetic clusters using G (z, θ_g) 13. classify clusters with D (x, ) to distinguish real from synthetic data 14. adjust G and D using min-max objective until discriminator cannot distinguish real from generated clusters 15. end while 16. for each cluster k: 17. for each node i in cluster k: 18. calculate = α * ()−β * ()−γ * (distance (i, )/) 19. end for 20. choose node with max as CH 21. end for 22. for each node i: 23. broadcast “Hello” message to discover neighbors 24. for each neighbor j of i: 25. = calculate Euclidean distance between node i and node j 26. //Initial pheromone setting 27. end for 28. end for 29. for each node i: 30. for each destination d and neighbor j: 31. calculate = /sum of weights over all neighbors 32. end for 33. end for 34. for each transmission on link (i, j): 35. if transmission is successful: 36. = Q/ 37. else: 38. = 0 39. end if 40. = (1−ρ) * + //Pheromone evaporation and reinforcement 41. end for 42. for each link (i, j): 43. calculate = [i][j]/[i][j] 44. if > : 45. mark link (i, j) as congested 46. consider alternative routes for load balancing 47. end if 48. end for 49. for each path from source node S to CH: 50. calculate = [i][j]/[i][j] 51. if < : 52. mark path as efficient 53. end if 54. = 1 55. for each link (i, j) in path: 56. * = (1− [i][j]) 57. end for 58. end for 59. define Z = sum ( * for each link (i, j)) 60. for each link (i, j): 61. if [i][j]/[i][j] > 0.7: 62. mark link (i, j) as congested 63. add (i, j) to congestion list 64. end if 65. end for 66. return the optimal route minimizing congestion and ensuring reliable data delivery |
4. Simulation and Results
5. Open Issue
6. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Sefati, S.; Navimipour, N.J. A QoS-aware service composition mechanism in the internet of things using a hidden-markov-model-based optimization algorithm. IEEE Internet Things J. 2021, 8, 15620–15627. [Google Scholar] [CrossRef]
- Sefati, S.S.; Craciunescu, R.; Arasteh, B.; Halunga, S.; Fratu, O.; Tal, I. Cybersecurity in a Scalable Smart City Framework Using Blockchain and Federated Learning for Internet of Things (IoT). Smart Cities 2024, 7, 2802–2841. [Google Scholar] [CrossRef]
- AlZyoud, F.; Tarawneh, M.; Almaghthawi, A.; Altalidi, A. A New Approach for Cluster Head Selection in Wireless Sensor Networks. Int. J. Online Biomed. Eng. 2024, 20, 39–50. [Google Scholar] [CrossRef]
- Sefati, S.S.; Halunga, S. Ultra-reliability and low-latency communications on the internet of things based on 5G network: Literature review, classification, and future research view. Trans. Emerg. Telecommun. Technol. 2023, 34, e4770. [Google Scholar] [CrossRef]
- Friess, P. Digitising the Industry-Internet of Things Connecting the Physical, Digital and Virtual Worlds; River Publishers: Nordjylland, Denmark, 2016. [Google Scholar]
- Lv, J.; Kim, B.-G.; Parameshachari, B.; Slowik, A.; Li, K. Large model-driven hyperscale healthcare data fusion analysis in complex multi-sensors. Inf. Fusion 2025, 115, 102780. [Google Scholar] [CrossRef]
- Al-Sarawi, S.; Anbar, M.; Alieyan, K.; Alzubaidi, M. Internet of Things (IoT) communication protocols. In Proceedings of the 2017 8th International Conference on Information Technology (ICIT), Amman, Jordan, 17–18 May 2017; IEEE: Piscataway Township, NJ, USA, 2017. [Google Scholar]
- Dvir, E.; Shifrin, M.; Gurewitz, O. Cooperative Multi-Agent Reinforcement Learning for Data Gathering in Energy-Harvesting Wireless Sensor Networks. Mathematics 2024, 12, 2102. [Google Scholar] [CrossRef]
- Sefati, S.S.; Arasteh, B.; Halunga, S.; Fratu, O.; Bouyer, A. Meet User’s Service Requirements in Smart Cities Using Recurrent Neural Networks and Optimization Algorithm. IEEE Internet Things J. 2023, 10, 22256–22269. [Google Scholar] [CrossRef]
- Al-Ward, H.; Tan, C.K.; Lim, W.H. Caching transient data in Information-Centric Internet-of-Things (IC-IoT) networks: A survey. J. Netw. Comput. Appl. 2022, 206, 103491. [Google Scholar] [CrossRef]
- Radhakrishnan, P.; Sugumar, P.K.; Ponnan, P.; Varadharajan, G.P. Correction to: Certificate-less Aggregate Signature Authentication Scheme (CLASAS) for secure and efficient data transmission in Wireless Sensor Networks (WSNs). Peer Peer Netw. Appl. 2024, 17, 3505. [Google Scholar] [CrossRef]
- Djahel, S.; Doolan, R.; Muntean, G.-M.; Murphy, J. A communications-oriented perspective on traffic management systems for smart cities: Challenges and innovative approaches. IEEE Commun. Surv. Tutor. 2014, 17, 125–151. [Google Scholar] [CrossRef]
- Nayak, D.; Ray, K.; Kar, T.; Mohanty, S.N. Fuzzy Rule Based Adaptive Block Compressive Sensing for WSN Application. Mathematics 2023, 11, 1660. [Google Scholar] [CrossRef]
- Sefati, S.S.; Haq, A.U.; Nidhi, R.; Craciunescu, R.; Halunga, S.; Mihovska, A.; Fratu, O. A Comprehensive Survey on Resource Management in 6G Network Based on Internet of Things. IEEE Access 2024, 12, 113741–113784. [Google Scholar] [CrossRef]
- Pan, Z.; Yu, W.; Yi, X.; Khan, A.; Yuan, F.; Zheng, Y. Recent progress on generative adversarial networks (GANs): A survey. IEEE Access 2019, 7, 36322–36333. [Google Scholar] [CrossRef]
- Blum, C. Ant colony optimization: Introduction and recent trends. Phys. Life Rev. 2005, 2, 353–373. [Google Scholar] [CrossRef]
- Ridha, A. Comparative study of transport protocols in WSN. In Proceedings of the 2014 Information and Communication Technologies Innovation and Application (ICTIA), Sousse, Tunisia, 6–8 March 2014; IEEE: Piscataway Township, NJ, USA, 2014. [Google Scholar]
- Aimtongkham, P.; Musikawan, P.; Kongsorot, Y.; So-In, C. A Novel Congestion Control Scheme Using Fuzzy Logic Systems to Enhance the Path Selection Criteria in Routing Protocols for Low-Power and Lossy Networks on the Internet of Things. SN Comput. Sci. 2024, 5, 610. [Google Scholar] [CrossRef]
- Bhat, R.V.; Haxhibeqiri, J.; Moerman, I.; Hoebeke, J. Network-and application-aware adaptive congestion control algorithm. J. Commun. Netw. 2024, 26, 344–355. [Google Scholar] [CrossRef]
- Andrade-Zambrano, A.R.; León, J.P.A.; Morocho-Cayamcela, M.E.; Cárdenas, L.L.; de la Cruz LLopis, L.J. A Reinforcement Learning Congestion Control Algorithm for Smart Grid Networks. IEEE Access 2024, 12, 75072–75092. [Google Scholar] [CrossRef]
- Narawade, V.; Kolekar, U.D. ACSRO: Adaptive cuckoo search based rate adjustment for optimized congestion avoidance and control in wireless sensor networks. Alex. Eng. J. 2018, 57, 131–145. [Google Scholar] [CrossRef]
- Kalaikumar, K.; Baburaj, E. Fuzzy enabled congestion control by cross layer protocol utilizing OABC in WSN: Combining MAC, routing, non-similar clustering and efficient data delivery. Wirel. Netw. 2020, 26, 1085–1103. [Google Scholar] [CrossRef]
- Antoniou, P.; Pitsillides, A.; Blackwell, T.; Engelbrecht, A.; Michael, L. Congestion control in wireless sensor networks based on bird flocking behavior. Comput. Netw. 2013, 57, 1167–1191. [Google Scholar] [CrossRef]
- Alipio, M.; Bures, M. A cache-aware congestion control mechanism using deep reinforcement learning for wireless sensor networks. Ad Hoc Netw. 2025, 166, 103678. [Google Scholar] [CrossRef]
- Mazloomi, N.; Gholipour, M.; Zaretalab, A. Efficient Fuzzy Methodology for Congestion Control in Wireless Sensor Networks. J. Frankl. Inst. 2024, 361, 107014. [Google Scholar] [CrossRef]
- Buyya, R.; Ilager, S.; Arroba, P. Energy-efficiency and sustainability in new generation cloud computing: A vision and directions for integrated management of data centre resources and workloads. Softw. Pract. Exp. 2024, 54, 24–38. [Google Scholar] [CrossRef]
- Çakmak, M. The Impact of Denial-of-Service Attacks and Queue Management Algorithms on Cellular Networks. J. Intell. Syst. Theory Appl. 2024, 7, 1–13. [Google Scholar] [CrossRef]
- Sunitha, G.; Kumar, S.D.; Kumar, B.V. Energy efficient hierarchical multi-path routing protocol to alleviate congestion in WSN. Int. J. Ad Hoc. Ubiquitous Comput. 2019, 32, 59–73. [Google Scholar] [CrossRef]
- Ghaffari, A. Congestion control mechanisms in wireless sensor networks: A survey. J. Netw. Comput. Appl. 2015, 52, 101–115. [Google Scholar] [CrossRef]
- Qu, L.; Assi, C.; Shaban, K. Delay-aware scheduling and resource optimization with network function virtualization. IEEE Trans. Commun. 2016, 64, 3746–3758. [Google Scholar] [CrossRef]
- Zeng, J.; Xiong, Y.; Liu, F.; Ye, J.; Tang, J. Uncovering the spatiotemporal patterns of traffic congestion from large-scale trajectory data: A complex network approach. Phys. A Stat. Mech. Its Appl. 2022, 604, 127871. [Google Scholar] [CrossRef]
- Wu, N.; Bi, Y.; Michael, N.; Tang, A.; Doyle, J.C.; Matni, N. A control-theoretic approach to in-network congestion management. IEEE/ACM Trans. Netw. 2018, 26, 2443–2456. [Google Scholar] [CrossRef]
- Dutta, A.; Samaniego Campoverde, L.M.; Tropea, M.; De Rango, F. A Comprehensive Review of Recent Developments in VANET for Traffic, Safety & Remote Monitoring Applications. J. Netw. Syst. Manag. 2024, 32, 73. [Google Scholar]
- Ryu, S.; Rump, C.; Qiao, C. Advances in internet congestion control. IEEE Commun. Surv. Tutor. 2003, 5, 28–39. [Google Scholar] [CrossRef]
- Archana, S.; Saravanan, N. Biologically inspired QoS aware routing protocol to optimize lifetime in sensor networks. In Proceedings of the 2014 International Conference on Recent Trends in Information Technology, Chennai, India, 10–12 April 2014; IEEE: Piscataway Township, NJ, USA, 2014; pp. 1–6. [Google Scholar]
- Feng, Y.; Zhang, W.; Feng, Z.; Zhong, X.; Liu, F. An MTD-driven Hybrid Defense Method Against DDoS Based on Markov Game in Multi-controller SDN-enabled IoT Networks. In Proceedings of the 2024 IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS), Guangzhou, China, 19–21 June 2024; IEEE: Piscataway Township, NJ, USA, 2024; pp. 1–6. [Google Scholar]
- Haq, A.U.; Sefati, S.S.; Nawaz, S.J.; Mihovska, A.; Beliatis, M.J. Need of UAVs and Physical Layer Security in Next-Generation Non-Terrestrial Wireless Networks: Potential Challenges and Open Issues. IEEE Open J. Vehicular Technol. 2025. Early Access. [Google Scholar] [CrossRef]
- Ekanayake, V.; Kelly IV, C.; Manohar, R. An ultra low-power processor for sensor networks. In Proceedings of the 11th International Conference on Architectural Support for Programming Languages and Operating Systems, Boston, MA, USA, 7–13 October 2004; pp. 27–36. [Google Scholar]
- Sari, E.K.; Wirara, A.; Harwahyu, R.; Sari, R.F. Lora characteristics analysis for IoT application using NS3 simulator. In Proceedings of the 2019 IEEE R10 Humanitarian Technology Conference (R10-HTC)(47129), Depok, Indonesia, 12–14 November 2019; IEEE: Piscataway Township, NJ, USA, 2019; pp. 205–210. [Google Scholar]
Author(s) | Proposed Method | Advantages | Disadvantages |
---|---|---|---|
Ridha [17] | Event-to-sink Reliable Transport (ESRT) | High reliability and availability in data transfer | Limited in load balancing and energy efficiency |
Aimtongkham, Musikawan [18] | Fuzzy Logic System (FLS)-based RPL for IoT | Mitigates congestion, reduces packet loss, optimizes energy usage | Increases computational demands on IoT devices, impacting network lifespan in congested environments |
Bhat, Haxhibeqiri [19] | Network and Application-Aware Adaptive Congestion Control (NACC) | Enhances adaptability and network efficiency; high throughput and performance in multi-flow tests | High overhead from continuous telemetry and application integration, limiting scalability in larger networks |
Andrade-Zambrano, León [20] | RL and DQN for UDP congestion control in smart grids | Improved packet delivery ratio, network throughput, and latency management | Scalability issues with increased network size, challenging real-time responsiveness in large deployments |
Narawade and Kolekar [21] | Adaptive Cuckoo Search Rate Optimization (ACSRO) | Efficient congestion control through dynamic rate adjustments | Computational complexity increases energy consumption in resource-limited WSN environments |
Kalaikumar and Baburaj [22] | Fuzzy Cross-Layer Optimization with OABC (FCOABC) | Maintains network stability, extends network lifespan by reducing CH congestion | Protocol complexity impacts scalability in large or resource-limited networks due to iterative processes |
Antoniou, Pitsillides [23] | Flock-based Congestion Control (Flock-CC) | Effective load balancing, resilient to node failures, scalable across network sizes | Delays in high-traffic scenarios, limited applicability in environments with rapid topology changes |
Alipio and Bures [24] | Deep Reinforcement Learning Cache-Aware Congestion Control (DRL-CaCC) | Improved data throughput and reduced packet loss by optimizing cache usage dynamically | High computational complexity limits feasibility in real time, resource-constrained WSN environments |
Mazloomi, Gholipour [25] | Fuzzy Structure and Genetic-Fuzzy (FSFG) | 32% improvement in packet delivery rate, 28% reduction in end-to-end delay | Complexity may restrict usability in highly resource-constrained networks, requiring further optimization |
Parameter | Value | Description |
---|---|---|
Network Area | 500 m × 500 m | Physical size of the simulated network |
Number of Sensor Nodes (N) | 100 | Total number of sensor nodes |
Number of Base Stations | 1 | Central base station for data aggregation |
Initial Node Energy | 2 Joules | Initial energy assigned to each sensor node |
Transmission Range | 100 m | Communication range for each sensor node |
Simulation Duration | 1000 s | Total time of simulation |
Packet Count | 10,000 | Total number of packets generated during simulation |
Average Packet Size | 512 bytes | Size of each data packet |
Traffic Load | Varied (low, moderate, high) | Different traffic loads to test congestion control |
Parameter | Value | Description |
---|---|---|
Pheromone Evaporation Rate (ρ) | 0.1 | Controls pheromone decay on paths |
Pheromone Deposit Factor (Q) | 0.5 | Strength of pheromone reinforcement |
Weight Parameters (α, β, γ, s, k) | 1.5, 1.2, 0.8, 1.0, 1.0 | Weights for energy, bandwidth, latency, steps, pheromone |
Parameter | Value | Description |
---|---|---|
Generator Layers | 128 neurons, 64 neurons | Number of neurons in hidden layers of generator |
Discriminator Layers | 128 neurons, 64 neurons | Number of neurons in hidden layers of discriminator |
Learning Rate | 0.001 | Learning rate for both generator and discriminator |
Batch Size | 64 | Batch size for training |
Input Noise | Gaussian noise | Type of noise input for generating synthetic clusters |
Link ID | Low Traffic Load CF | Moderate Traffic Load CF | High Traffic Load CF |
---|---|---|---|
Link 1 | 0.20 | 0.45 | 0.75 |
Link 2 | 0.15 | 0.40 | 0.70 |
Link 3 | 0.18 | 0.42 | 0.68 |
Link 4 | 0.12 | 0.38 | 0.72 |
Link 5 | 0.22 | 0.46 | 0.78 |
Link 6 | 0.14 | 0.41 | 0.74 |
Link 7 | 0.16 | 0.39 | 0.71 |
Link 8 | 0.13 | 0.37 | 0.69 |
Link 9 | 0.19 | 0.43 | 0.73 |
Link 10 | 0.17 | 0.44 | 0.76 |
Link 11 | 0.21 | 0.47 | 0.79 |
Link 12 | 0.11 | 0.35 | 0.67 |
Link 13 | 0.20 | 0.43 | 0.75 |
Link 14 | 0.18 | 0.41 | 0.70 |
Link 15 | 0.12 | 0.36 | 0.66 |
Link 16 | 0.15 | 0.39 | 0.72 |
Link 17 | 0.13 | 0.38 | 0.69 |
Link 18 | 0.14 | 0.40 | 0.73 |
Link 19 | 0.16 | 0.42 | 0.71 |
Link 20 | 0.10 | 0.34 | 0.65 |
Traffic Load | Network Lifetime (s) | Percentage of Nodes Operational After 1000 s |
---|---|---|
Low Traffic Load | 5200 | 92% |
Moderate Traffic Load | 3800 | 78% |
High Traffic Load | 2600 | 62% |
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. |
© 2025 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
Sefati, S.S.; Arasteh, B.; Craciunescu, R.; Comsa, C.-R. Intelligent Congestion Control in Wireless Sensor Networks (WSN) Based on Generative Adversarial Networks (GANs) and Optimization Algorithms. Mathematics 2025, 13, 597. https://doi.org/10.3390/math13040597
Sefati SS, Arasteh B, Craciunescu R, Comsa C-R. Intelligent Congestion Control in Wireless Sensor Networks (WSN) Based on Generative Adversarial Networks (GANs) and Optimization Algorithms. Mathematics. 2025; 13(4):597. https://doi.org/10.3390/math13040597
Chicago/Turabian StyleSefati, Seyed Salar, Bahman Arasteh, Razvan Craciunescu, and Ciprian-Romeo Comsa. 2025. "Intelligent Congestion Control in Wireless Sensor Networks (WSN) Based on Generative Adversarial Networks (GANs) and Optimization Algorithms" Mathematics 13, no. 4: 597. https://doi.org/10.3390/math13040597
APA StyleSefati, S. S., Arasteh, B., Craciunescu, R., & Comsa, C.-R. (2025). Intelligent Congestion Control in Wireless Sensor Networks (WSN) Based on Generative Adversarial Networks (GANs) and Optimization Algorithms. Mathematics, 13(4), 597. https://doi.org/10.3390/math13040597