Machine Learning Techniques for Energy Efficiency and Anomaly Detection in Hybrid Wireless Sensor Networks
Wireless sensor networks (WSNs) are among the most popular wireless technologies for sensor communication purposes nowadays. Usually, WSNs are developed for specific applications, either monitoring purposes or tracking purposes, for indoor or outdoor environments, where limited battery power is a ma...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/14/11/3125 |
| _version_ | 1827691388446179328 |
|---|---|
| author | Mohit Mittal Rocío Pérez de Prado Yukiko Kawai Shinsuke Nakajima José E. Muñoz-Expósito |
| author_facet | Mohit Mittal Rocío Pérez de Prado Yukiko Kawai Shinsuke Nakajima José E. Muñoz-Expósito |
| author_sort | Mohit Mittal |
| collection | DOAJ |
| description | Wireless sensor networks (WSNs) are among the most popular wireless technologies for sensor communication purposes nowadays. Usually, WSNs are developed for specific applications, either monitoring purposes or tracking purposes, for indoor or outdoor environments, where limited battery power is a main challenge. To overcome this problem, many routing protocols have been proposed through the last few years. Nevertheless, the extension of the network lifetime in consideration of the sensors capacities remains an open issue. In this paper, to achieve more efficient and reliable protocols according to current application scenarios, two well-known energy efficient protocols, i.e., Low-Energy Adaptive Clustering hierarchy (LEACH) and Energy–Efficient Sensor Routing (EESR), are redesigned considering neural networks. Specifically, to improve results in terms of energy efficiency, a Levenberg–Marquardt neural network (LMNN) is integrated. Furthermore, in order to improve the performance, a sub-cluster LEACH-derived protocol is also proposed. Simulation results show that the Sub-LEACH with LMNN outperformed its competitors in energy efficiency. In addition, the end-to-end delay was evaluated, and Sub-LEACH protocol proved to be the best among existing strategies. Moreover, an intrusion detection system (IDS) has been proposed for anomaly detection based on the support vector machine (SVM) approach for optimal feature selection. Results showed a 96.15% accuracy—again outperforming existing IDS models. Therefore, satisfactory results in terms of energy efficiency, end-to-end delay and anomaly detection analysis were attained. |
| first_indexed | 2024-03-10T11:00:02Z |
| format | Article |
| id | doaj.art-fb968396c7c44fd280aa3c6a3339df78 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T11:00:02Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-fb968396c7c44fd280aa3c6a3339df782023-11-21T21:35:49ZengMDPI AGEnergies1996-10732021-05-011411312510.3390/en14113125Machine Learning Techniques for Energy Efficiency and Anomaly Detection in Hybrid Wireless Sensor NetworksMohit Mittal0Rocío Pérez de Prado1Yukiko Kawai2Shinsuke Nakajima3José E. Muñoz-Expósito4Centre de Recherche en Informatique, Signal et Automatique de Lille, INRIA, 59655 Villeneuve-d’Ascq, FranceTelecommunication Engineering Department, University of Jaén, 23071 Jaén, SpainDepartment of Information Science and Engineering, Kyoto Sangyo University, Kamingamo, Kita-ku, Kyoto 603-8555, JapanDepartment of Information Science and Engineering, Kyoto Sangyo University, Kamingamo, Kita-ku, Kyoto 603-8555, JapanTelecommunication Engineering Department, University of Jaén, 23071 Jaén, SpainWireless sensor networks (WSNs) are among the most popular wireless technologies for sensor communication purposes nowadays. Usually, WSNs are developed for specific applications, either monitoring purposes or tracking purposes, for indoor or outdoor environments, where limited battery power is a main challenge. To overcome this problem, many routing protocols have been proposed through the last few years. Nevertheless, the extension of the network lifetime in consideration of the sensors capacities remains an open issue. In this paper, to achieve more efficient and reliable protocols according to current application scenarios, two well-known energy efficient protocols, i.e., Low-Energy Adaptive Clustering hierarchy (LEACH) and Energy–Efficient Sensor Routing (EESR), are redesigned considering neural networks. Specifically, to improve results in terms of energy efficiency, a Levenberg–Marquardt neural network (LMNN) is integrated. Furthermore, in order to improve the performance, a sub-cluster LEACH-derived protocol is also proposed. Simulation results show that the Sub-LEACH with LMNN outperformed its competitors in energy efficiency. In addition, the end-to-end delay was evaluated, and Sub-LEACH protocol proved to be the best among existing strategies. Moreover, an intrusion detection system (IDS) has been proposed for anomaly detection based on the support vector machine (SVM) approach for optimal feature selection. Results showed a 96.15% accuracy—again outperforming existing IDS models. Therefore, satisfactory results in terms of energy efficiency, end-to-end delay and anomaly detection analysis were attained.https://www.mdpi.com/1996-1073/14/11/3125LEACH protocolEESR protocolneural networkssupport vector machineenergy efficiencyend-to-end delay |
| spellingShingle | Mohit Mittal Rocío Pérez de Prado Yukiko Kawai Shinsuke Nakajima José E. Muñoz-Expósito Machine Learning Techniques for Energy Efficiency and Anomaly Detection in Hybrid Wireless Sensor Networks Energies LEACH protocol EESR protocol neural networks support vector machine energy efficiency end-to-end delay |
| title | Machine Learning Techniques for Energy Efficiency and Anomaly Detection in Hybrid Wireless Sensor Networks |
| title_full | Machine Learning Techniques for Energy Efficiency and Anomaly Detection in Hybrid Wireless Sensor Networks |
| title_fullStr | Machine Learning Techniques for Energy Efficiency and Anomaly Detection in Hybrid Wireless Sensor Networks |
| title_full_unstemmed | Machine Learning Techniques for Energy Efficiency and Anomaly Detection in Hybrid Wireless Sensor Networks |
| title_short | Machine Learning Techniques for Energy Efficiency and Anomaly Detection in Hybrid Wireless Sensor Networks |
| title_sort | machine learning techniques for energy efficiency and anomaly detection in hybrid wireless sensor networks |
| topic | LEACH protocol EESR protocol neural networks support vector machine energy efficiency end-to-end delay |
| url | https://www.mdpi.com/1996-1073/14/11/3125 |
| work_keys_str_mv | AT mohitmittal machinelearningtechniquesforenergyefficiencyandanomalydetectioninhybridwirelesssensornetworks AT rocioperezdeprado machinelearningtechniquesforenergyefficiencyandanomalydetectioninhybridwirelesssensornetworks AT yukikokawai machinelearningtechniquesforenergyefficiencyandanomalydetectioninhybridwirelesssensornetworks AT shinsukenakajima machinelearningtechniquesforenergyefficiencyandanomalydetectioninhybridwirelesssensornetworks AT joseemunozexposito machinelearningtechniquesforenergyefficiencyandanomalydetectioninhybridwirelesssensornetworks |