An Energy-Efficient Dual Prediction Scheme Using LMS Filter and LSTM in Wireless Sensor Networks for Environment Monitoring

• Published in: IEEE internet of things journal Vol. 6; no. 4; pp. 6736 - 6747
• Main Authors: Shu, Tongxin, Chen, Jiahong, Bhargava, Vijay K., de Silva, Clarence W.
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.08.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Correlation; Data communication; Data transmission; Dual prediction scheme (DPS); Electric power supplies; Energy conservation; Energy consumption; Energy transmission; Environmental monitoring; Error detection; least mean square (LMS); long short-term memory (LSTM); Nodes; Prediction algorithms; Predictions; Predictive models; Remote sensors; Sensors; wireless sensor network (WSN); Wireless sensor networks
• ISSN: 2327-4662; 2327-4662
• DOI: 10.1109/JIOT.2019.2911295

Environmental monitoring is a practical application where a wireless sensor network (WSN) may be utilized effectively. However, the energy consumption issues have become a major concern in using a WSN, particularly in remote locations without readily accessible electrical power supply. In general, the activities of data transmission among sensor nodes and the gateway (GW) can be a significant fraction of the total energy consumption within a WSN. Hence, reducing the number and the duration of transmissions as much as possible while maintaining a high level of data accuracy can be an effective strategy for saving energy. To achieve this objective, a least mean square (LMS) filter is used for a dual prediction scheme (DPS), in this paper. The DPS is data quality-based, allowing both the sensor nodes and the GW to predict the data simultaneously. Only when the error between the predicted data and the real sensed data exceeds a predefined threshold, the sensor nodes will send the sensed data to the GW/another node and consequently will update the coefficients of the filter. It is observed that, with this scheme, the total number of transmissions and their overall duration can be effectively reduced, and therefore, further energy savings can be realized. With the developed methodologies, at least 62.3% of the total energy for data transmission could be saved while achieving a 93.1% prediction accuracy.