Reducing energy consumption of wireless sensor networks using rules and extreme learning machine algorithm

Abstract

Wireless sensor networks consist of a collection of sensors to monitor physical or environmental events. Nowadays, the sensor networks are used in important applications like military, health and civilian monitoring. Since it is a wireless medium, deployed in remote locations and resource-constrained nature, the sensor networks are easily vulnerable to attacks. The attack creates significant damages to the sensor networks. To avoid these problems, intrusion detection system (IDS) is implemented at the base station to filter any abnormal packets. In the proposed system, a survey is made on the attacks and rules to detect the attacks. Filtering the attacks using rule-based IDS at the sensor nodes would reduce the amount of packet transmission to the base station which, in turn, would reduce the energy consumption of the sensor network. Extreme learning machine (ELM) algorithm is implemented at the base station to detect the abnormal packets. The experimental result shows the performance of different classification techniques and cross-layer rules over the NSL-KDD and real-time datasets. The detection rate of the ELM algorithm is higher compared to other systems.

Keywords

• security of data
• wireless sensor networks
• learning (artificial intelligence)
• telecommunication security
• telecommunication computing
• energy consumption
• power engineering computing
• energy consumption
• wireless sensor networks
• extreme learning machine algorithm
• sensor network
• health
• civilian monitoring
• base station
• rule-based IDS
• sensor nodes
• attack detection
• attack filtering
• intrusion detection system
• abnormal packet filtering
• classification techniques
• cross-layer rules