Search

During the data gathering process in sensor networks, lots of transmitted data packets can be lost due to the limiting node energy and the influence of data redundancy. In order to solve this problem, a prediction model is proposed for lost packets based on data reconstruction on lossy links in sensor networks. In this model, retransmission is adopted for data recovery when a random packet loss is predicted while prediction algorithms based on time sequences can be employed for data recovery when a random packet loss cannot be predicted. The operation of the whole system can still be guaranteed with this model when the packet loss probability of the network is lower than 15% while the relative error for data reconstruction remains between 0.17%~0.22% when the packet loss probability is higher than 22%. It is thus proven that this prediction model exhibits a strong stability and flexibility.

With the wide application of the cloud computing, the contradiction between high energy cost and low efficiency becomes increasingly prominent. In this article, to solve the problem of energy consumption, a resource scheduling and load balancing fusion algorithm with deep learning strategy is presented. Compared with the corresponding evolutionary algorithms, the proposed algorithm can enhance the diversity of the population, avoid the prematurity to some extent, and have a faster convergence speed. The experimental results show that the proposed algorithm has the most optimal ability of reducing energy consumption of data centers.