A Real-time Forecasting Method of Entities in Internet of Things Based on Cycle Models
Kong Ying-hu · Telecommunication Engineering · 2013
The analysis and processing of vast amounts of data of entities in the Internet of Things( IOT)has become the basis for the development of IOT application layer. Many applications need to predict the states of entities in IOT. States of entities in IOT are strong real-time and high dynamic. By judging cycle mode of entities in IOT and establishing the time window of a specific period of time,reasonable prediction model is used to predict the probability value of future state of entities. The prediction method is of short time-consuming and high accuracy. With this method,the prediction result can be given in 2 ~ 4 s and it is in accordance with actual one. It plays a role of good indicator in the decision-making analysis of IOT application layer.