Due to the challenge of increasing data volume, the traditional trust model is unable to manage data with high efficiency and effectively extract useful information hidden in big data. To fully utilize big data and combine machine learning with trust evaluation, a trust evaluation model based on Long short‐term memory (LSTM) is presented. The powerful learning ability, expressive ability and dynamic timing of LSTM can be applied to study data while avoiding the vanishing and exploding gradient phenomena of traditional Recurrent neural networks (RNNs) to ensure that the model can learn sequences of random length and provide accurate trust evaluation. Targeting the performance instability caused by the LSTM model's random initialization of weights and thresholds, Particle swarm optimization (PSO), one of the intelligent algorithms, is introduced to find global optimal initial weights and thresholds. Experiments proved that the trust model proposed in this paper has high accuracy and contributes a new idea for trust evaluation in big data environments.
In recent years, high energy consumption has gradually become a prominent problem in a data center. With the advent of cloud computing, computing and storage resources are bringing greater challenges to energy consumption. Virtual machine (VM) initial placement plays an important role in affecting the size of energy consumption. In this paper, we use binary particle swarm optimization (BPSO) algorithm to design a VM placement strategy for low energy consumption measured by proposed energy efficiency fitness, and this strategy needs multiple iterations and updates for VM placement. Finally, the strategy proposed in this paper is compared with other four strategies through simulation experiments. The results show that our strategy for VM placement has better performance in reducing energy consumption than the other four strategies, and it can use less active hosts than others.
With the development of wireless sensor networks, certain network problems have become more prominent, such as limited node resources, low data transmission security, and short network life cycles. To solve these problems effectively, it is important to design an efficient and trusted secure routing algorithm for wireless sensor networks. Traditional ant-colony optimization algorithms exhibit only local convergence, without considering the residual energy of the nodes and many other problems. This paper introduces a multi-attribute pheromone ant secure routing algorithm based on reputation value (MPASR). This algorithm can reduce the energy consumption of a network and improve the reliability of the nodes’ reputations by filtering nodes with higher coincidence rates and improving the method used to update the nodes’ communication behaviors. At the same time, the node reputation value, the residual node energy and the transmission delay are combined to formulate a synthetic pheromone that is used in the formula for calculating the random proportion rule in traditional ant-colony optimization to select the optimal data transmission path. Simulation results show that the improved algorithm can increase both the security of data transmission and the quality of routing service.
Nowadays, anyone carrying a mobile device can enjoy the various location-based services provided by the Internet of Things (IoT). ‘Aggregate nearest neighbor query’ is a new type of location-based query which asks the question, ‘what is the best location for a given group of people to gather?’ There are numerous, promising applications for this type of query, but it needs to be done in a secure and private way. Therefore, a trajectory privacy-preserving scheme, based on a trusted anonymous server (TAS) is proposed. Specifically, in the snapshot queries, the TAS generates a group request that satisfies the spatial K-anonymity for the group of users—to prevent the location-based service provider (LSP) from an inference attack—and in continuous queries, the TAS determines whether the group request needs to be resent by detecting whether the users will leave their secure areas, so as to reduce the probability that the LSP reconstructs the users’ real trajectories. Furthermore, an aggregate nearest neighbor query algorithm based on strategy optimization, is adopted, to minimize the overhead of the LSP. The response speed of the results is improved by narrowing the search scope of the points of interest (POIs) and speeding up the prune of the non-nearest neighbors. The security analysis and simulation results demonstrated that our proposed scheme could protect the users’ location and trajectory privacy, and the response speed and communication overhead of the service, were superior to other peer algorithms, both in the snapshot and continuous queries.
Trust mechanism will be an important trend in the field of security for open network. But, as an important factor risk is little considered in trust model. In this paper, Further works are done in trust and risk separately. In course of trust propagation, direct interaction information of the middle recommendation node is presented, which expresses the importance of subjective factor. About risk mechanism, two important factors are considered to improve the corresponding algorithms: length-limit of the risk propagation path and pre-operation process before integrating these paths. With the help of fuzzy logic technology, the trusted decision mechanism is presented which is based on trust and risk. Experimental results and some cases show that the new trusted decision mechanism is reasonable and high-powered.