Data transmission reduction using prediction and aggregation techniques in IoT-based wireless sensor networks

Currently, broad ranges of economic sectors exploit the Internet of Things (IoT) and Wireless Sensor Networks (WSNs) technology generating problems to be managing, processing and organizing the big data streams. Given the inherent sensor constraints (battery-dependent life, lack of memory space, limited processor power), there is a need for systems capable of reducing data transmission flux of the distributed IoT-based WSNs applications to mitigate the continuously increasing network traffic. Prediction and data aggregation techniques are promising solutions to meet this requirement. These techniques are particularly powerful solutions in forecasting processes where a huge data to be collected, transmitted and recorded. This is right even if we consider the integration of IoT-based WSNs with cloud computing technology. This paper proposes the combination of the recently developed prediction scheme EADPS (Extended Adaptive Dual Prediction Scheme) and the temporal correlation based data aggregation technique as a power tool to address the problem of communication reduction in connected IoT-based WSNs. First, we studied separately the impact of each technique before considering their combination. To achieve this goal, we consider the multi-hop ring model of the IoT-based WSNs. The results show that the aggregation technique is powerful compared to the DPS prediction scheme but loses its superiority for small WSNs size (with lesser than five rings) when the EADPS schema is applied. In addition, the data correlation has a feeble impact on reduction of transmission rates. According to the imposed tolerance thresholds, we show that the proposed scheme reduced the average transmission rates in the range 85%-96% for the entire network. The obtained results are presented and discussed.