Low-Overhead and High-Precision Prediction Model for Content-Based Sensor Search in the Internet of Things

A growing number of Internet-connected sensors have already promoted the advance of sensor search service. Accessing all available objects to find the sought sensor results in huge communication overhead, thus a low-overhead and high-precision prediction model (LHPM) is proposed to improve the sensor search efficiency. We design the approximation method to lower the reporting energy cost. Then a multistep prediction method is proposed to accurately estimate the sensor state. Furthermore, a sensor ranking method is presented to assess the matching probabilities of sensors, so as to effectively reduce the communication overhead of the search process. Simulation results demonstrate the validity of the proposed prediction model in the area of content-based sensor search.