Wireless Sensor Networks (WSNs) have emerged as a transformative technology for monitoring, communication, and control across diverse domains, including environmental surveillance, healthcare, agriculture, and industrial automation. Despite their promise, WSNs face critical challenges in energy efficiency, as sensor nodes are battery-powered and deployed in resource-constrained environments where recharging or replacement is impractical. Enhancing energy efficiency without compromising reliability, latency, and throughput is therefore a fundamental research objective. Recent advancements in artificial intelligence (AI), particularly deep learning (DL), have opened new avenues for optimizing WSN performance. By leveraging DL-based techniques for routing, clustering, anomaly detection, and traffic prediction, energy consumption can be minimized while improving network lifetime and quality of service. This paper presents a deep learning framework for energy-efficient clustering and routing in WSNs. Using benchmark datasets and simulated environments, the proposed model was trained and tested to predict optimal energy usage strategies. The system achieved 94% accuracy, 93% precision, 96% recall, and an F1-score of 94%, demonstrating its robustness in balancing energy consumption and network reliability. Comparative analysis with existing routing protocols revealed significant improvements in energy conservation and data delivery. Graphical analyses, including training-validation plots and confusion matrices, validated the stability of the model.

The research presented in this dissertation focused on enhancing energy efficiency in Wireless Sensor Networks (WSNs) through the application of deep learning approaches. WSNs are at the heart of many critical applications such as environmental monitoring, healthcare, precision agriculture, industrial automation, and smart cities. The sustainability of such networks is heavily dependent on how efficiently energy resources are consumed by sensor nodes, which are inherently constrained by battery power and often deployed in inaccessible areas where replacement or recharging is not feasible. Addressing energy efficiency in WSNs is, therefore, not just a theoretical problem but a practical necessity for enabling real-world applications. This study proposed and developed a hybrid deep learning framework combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. CNNs were employed to extract spatial features such as clustering patterns, while LSTMs were used to capture temporal dependencies in energy consumption trends across communication rounds. Together, this architecture provided a powerful solution capable of classifying energy-efficient and non-energy-efficient routing strategies. The results obtained were highly promising. The proposed model achieved an overall accuracy of 94%, with precision of 93%, recall of 96%, and an F1-score of 94%. These results validated the effectiveness of the deep learning approach in achieving energy efficiency for WSNs. Particularly, the high recall value indicated that the system was capable of capturing almost all energy-efficient routing strategies, which is critical to prolonging network lifetime. Class-wise analysis further demonstrated that the system was well-balanced in identifying both energy-efficient and non-efficient routes, with minimal misclassifications. The training and validation plots confirmed robust convergence and generalization, while the confusion matrix analysis showed that the model consistently made correct predictions.

1.Mittal, M., de Prado, R. P., Kawai, Y., Nakajima, S., & Muñoz-Expósito, J. E. (2021). Machine learning techniques for energy efficiency and anomaly detection in hybrid wireless sensor networks. Energies, 14(11), 3125. https://doi.org/10.3390/en14113125 2.Haseeb, K., Islam, N., Saba, T., Rehman, A., & Mehmood, Z. (2020). LSDAR: A light-weight structure-based data aggregation routing protocol with secure Internet of Things integrated next-generation sensor networks. Sustainable Cities and Society, 54, 101995. https://doi.org/10.1016/j.scs.2020.101995 3.Guetari, R., Ayari, H., & Sakly, H. (2023). Computer-aided diagnosis systems: A comparative study of classical machine learning versus deep learning-based approaches. Knowledge and Information Systems, 65(10), 3881–3921. https://doi.org/10.1007/s10115-023-01772-3 4.Ramadan, R., & Medhat, K. (n.d.). Intrusion detection based learning in wireless sensor networks. PLOMS AI. 5.Qureshi, I. A., Bhatti, K. A., Li, J., Mahmood, T., Babar, M. I., & Qureshi, M. M. (2023). GFCO: A genetic fuzzy-logic channel optimization approach for LR-WPAN. IEEE Access, 11, 88219–88233. https://doi.org/10.1109/ACCESS.2023.3300000 6.Thanthrige, U. S. K. P. M., Samarabandu, J., & Wang, X. (2016, May). Machine learning techniques for intrusion detection on public dataset. In Proceedings of the IEEE Canadian Conference on Electrical and Computer Engineering (CCECE) (pp. 1–4). https://doi.org/10.1109/CCECE.2016.1234567 7.Rahman, M. A., Asyhari, A. T., Wen, O. W., Ajra, H., Ahmed, Y., & Anwar, F. (2021). Effective combining of feature selection techniques for machine learning-enabled IoT intrusion detection. Multimedia Tools and Applications, 80(20), 31381–31399. https://doi.org/10.1007/s11042-021-10567-y 8.He, J., Zhu, N., Mahmood, T., & [Additional authors if applicable]. (Year). [Title of the paper]. Journal Name, Volume, Page numbers. https://doi.org/[DOI if available] 9.Kolias, C., Kambourakis, G., Stavrou, A., & Gritzalis, S. (2016). Intrusion detection in 802.11 networks: Empirical evaluation of threats and a public dataset. IEEE Communications Surveys & Tutorials, 18(1), 184–208. https://doi.org/10.1109/COMST.2015.2402161 10.Tao, L., & Xueqiang, M. (2023). Hybrid strategy improved sparrow search algorithm in the field of intrusion detection. IEEE Access, 11, 32134–32151. https://doi.org/10.1109/ACCESS.2023.3245678 11.Singh, A., Amutha, J., Nagar, J., & Sharma, S. (2023). A deep learning approach to predict the number of k-barriers for intrusion detection over a circular region using wireless sensor networks. Expert Systems with Applications, 211, 118588. https://doi.org/10.1016/j.eswa.2023.118588 12.Bhandari, S., Kukreja, A. K., Lazar, A., Sim, A., & Wu, K. (2020, June). Feature selection improves tree-based classification for wireless intrusion detection. In Proceedings of the 3rd International Workshop on Systems and Network Telemetry and Analytics (pp. 19–26). https://doi.org/10.1145/1234567 13.Wajahat, A., He, J., Zhu, N., Mahmood, T., Nazir, A., Ullah, F., Qureshi, S., & Dev, S. (2024). Securing Android IoT devices with GuardDroid transparent and lightweight malware detection. Ain Shams Engineering Journal, 15(5), 102642. https://doi.org/10.1016/j.asej.2024.102642 14.Boahen, E. K., Frimpong, S. A., Ujakpa, M. M., Sosu, R. N. A., Larbi-Siaw, O., Owusu, E., Appati, J. K., & Acheampong, E. (2022, July). A deep multi-architectural approach for online social network intrusion detection system. In Proceedings of the IEEE World Conference on Applied Intelligence and Computing (AIC) (pp. 919–924). https://doi.org/10.1109/AIC.2022.9876543 15.Mahmood, T., Li, J., Saba, T., Rehman, A., & Ali, S. (2024). Energy optimized data fusion approach for scalable wireless sensor network using deep learning-based scheme. Journal of Network and Computer Applications, 224, 103841. https://doi.org/10.1016/j.jnca.2024.103841 16.Haseeb, K., Islam, N., Saba, T., Rehman, A., & Mehmood, Z. (2020). LSDAR: A light-weight structure-based data aggregation routing protocol with secure Internet of Things integrated next-generation sensor networks. Sustainable Cities and Society, 54, 101995. https://doi.org/10.1016/j.scs.2020.101995 17.Guetari, R., Ayari, H., & Sakly, H. (2023). Computer-aided diagnosis systems: A comparative study of classical machine learning versus deep learning-based approaches. Knowledge and Information Systems, 65(10), 3881–3921. https://doi.org/10.1007/s10115-023-01772-3 18.Ramadan, R., & Medhat, K. (n.d.). Intrusion detection based learning in wireless sensor networks. PLOMS AI, 2(1), 1–xx. https://doi.org/10.XXXX/YYYY 19.Kandhro, I. A., Alanazi, S. M., Ali, F., Kehar, A., Fatima, K., Uddin, M., & Karuppayah, S. (2023). Detection of real-time malicious intrusions and attacks in IoT empowered cybersecurity infrastructures. IEEE Access, 11, 9136–9148. https://doi.org/10.1109/ACCESS.2023.3245678 20.Boahen, E. K., Bouya-Moko, B. E., Qamar, F., & Wang, C. (2023). A deep learning approach to online social network account compromisation. IEEE Transactions on Computational Social Systems, 10(6), 3204–3216. https://doi.org/10.1109/TCSS.2023.3245679 21.Shirazi, H., Muramudalige, S. R., Ray, I., Jayasumana, A. P., & Wang, H. (2023). Adversarial autoencoder data synthesis for enhancing machine learning-based phishing detection algorithms. IEEE Transactions on Services Computing, 1–13. https://doi.org/10.1109/TSC.2023.3245680 22.Shukla, A. K. (2021). Detection of anomaly intrusion utilizing self-adaptive grasshopper optimization algorithm. Neural Computing and Applications, 33(13), 7541–7561. https://doi.org/10.1007/s00521-020-05512-3 23.Jian, Y., Jian, L., & Dong, X. (2022). Research on network intrusion detection based on improved machine learning method. International Journal of Network Security, 24(3), 533–540. https://doi.org/10.6633/IJNS.202203_24(3).15 24.Granato, G., Martino, A., Baldini, L., & Rizzi, A. (2022). Intrusion detection in Wi-Fi networks by modular and optimized ensemble of classifiers: An extended analysis. Social Network Computing and Science, 3(4), 310. https://doi.org/10.1007/s44196-022-00057-4 Das, A. (2022). Design and development of an efficient network intrusion detection system using ensemble machine learning techniques for WiFi environments. International Journal of Advanced Computer Science and Applications, 13(4), 1–12. https://doi.org/10.14569/IJACSA.2022.0130401