An Adaptive Prediction Strategy with Clustering in Wireless Sensor Network
- PDF / 1,734,939 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 50 Downloads / 210 Views
An Adaptive Prediction Strategy with Clustering in Wireless Sensor Network Rajeev Kumar1 · Vibha Jain2 · Naveen Chauhan1 · Narottam Chand1 Received: 18 December 2019 / Revised: 1 September 2020 / Accepted: 18 September 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In Wireless Sensor Network, sensed data reflects two types of correlations of physical attributes: spatial and temporal. In this paper, a scheme named, Adaptive Prediction Strategy with ClusTering (APSCT) is proposed. In APSCT, a data-driven clustering and grey prediction model is used to exploit both the correlations. APSCT minimizes the transmission of messages in the network. However, the use of prediction includes additional computation overhead. There is a trade-off between prediction accuracy and energy consumption in computation and communication in wireless networks. This paper also gives an approach to calculate the upper and lower bound of the prediction interval which is used to evaluate different confidence levels and provides an energy-efficient sensor environment. Simulation is carried out on real-world data collected by Intel Berkeley Lab and results are compared with existing approaches. Keywords WSN · Adaptive prediction · APSCT · Grey prediction · Spatial and temporal
1 Introduction Wireless Sensor Networks (WSNs) consist of sensing devices (nodes) deployed in the hostile environment to monitor or analyze different situations. Healthcare, agriculture, environmental monitoring, traffic control, industrial process, intrusion detection, outlier detection, etc. are some areas where WSNs are widely used [1]. Sensor nodes sense different conditions and send the appropriate values to the sink for further computation. The sink can reside anywhere in the network: inside or outside. The links between sink and source are bidirectional. It can be used either by the sink to request any information and to send new configuration * Rajeev Kumar [email protected] Vibha Jain [email protected] Naveen Chauhan [email protected] Narottam Chand [email protected] 1
Department of Computer Science & Engineering, National Institute of Technology, Hamirpur, India
Department of Computer Engineering, Netaji Subhas University of Technology, New Delhi, India
2
messages or by sensing nodes to send data to the sink [2]. These sensor nodes are constraint by limited battery power as they are usually deployed in remote locations, which makes the replacement/recharge of their battery impossible. Due to such factors, energy conservation is the major concern in WSNs. Different strategies are used to limit the utilization of energy, for instance, scheduling the sensor state between sleep and active, clustering, routing and data-aggregation, data compression, data prediction, etc [3, 4]. Several non-critical applications of sensor networks can tolerate some amount of error in the result, as sensor nodes may have uncertainty in sample data they collect [5–7]. Since nodes are deployed densely, two types of correlations are found in
Data Loading...