With the continuous increase of maritime activities, maritime Internet of Things (M-IoT) devices are also growing explosively, which puts forward higher requirements for maritime networks with limited resources and complex environment. As the basis of 6G edge intelligence, edge computing technology can be adopted to deal with massive heterogeneous ocean data effectively to meet the needs of different maritime application scenarios. To improve the execution efficiency of maritime edge computing under the constraints of delay and energy consumption, we propose an edge computing network architecture for M-IoT based on the space-air-ground-sea integrated communication network of 6G, and put forward an intelligent task offloading algorithm based on Reinforcement Learning(RL), which migrates heavy computation tasks to suitable servers by means of cloud-edge-end cooperation. Simulation results show the superiority of the algorithm in time delay and energy efficiency.
This article considers the group consistency of second-order MAS with directly connected spanning tree communication topology. Because the MAS is divided into several groups, we proposed a group consistency control method based on intermittent control, and the range of parameters is given when the system achieves consensus. The protocol can realize periodic control and reduce the working hours of the controller in period. Furthermore, the group consistency of MAS is turn to the stability analysis of error, and a group consistency protocol of MAS with time-delays is designed. Finally, two examples are used for verify the theory.
Current Industrial Internet faces serious threats where attackers propagate malicious flows, resulting in communication failures in the Industrial Internet. In this work, we propose a practical and novel method to detect malicious traffic attack in real time with high accuracy. Our primary idea is to capture network flow, extract adequate network flow features, construct a long short-term memory (LSTM) based deep learning model, and identify the property of the corresponding network flow. Whether the network suffers attack or not is then determined according to the detection results. The corresponding prototype is also implemented in the Industrial Internet which is equipped with Software Defined Networking (SDN). Experimental results validate that the proposed method is effective in defending against malicious traffic attack in real-world network.
Intrusion detection is a traditional practice of security experts, however, there are several issues which still need to be tackled. Therefore, in this paper, after highlighting these issues, we present an architecture for a hybrid Intrusion Detection System (IDS) for an adaptive and incremental detection of both known and unknown attacks. The IDS is composed of supervised and unsupervised modules, namely, a Deep Neural Network (DNN) and the K-Nearest Neighbors (KNN) algorithm, respectively. The proposed system is near-autonomous since the intervention of the expert is minimized through the active learning (AL) approach. A query strategy for the labeling process is presented, it aims at teaching the supervised module to detect unknown attacks and improve the detection of the already-known attacks. This teaching is achieved through sliding windows (SW) in an incremental fashion where the DNN is retrained when the data is available over time, thus rendering the IDS adaptive to cope with the evolutionary aspect of the network traffic. A set of experiments was conducted on the CICIDS2017 dataset in order to evaluate the performance of the IDS, promising results were obtained.
Particle filtering is an indispensable method for non-Gaussian state estimation, but it has some problems, such as particle degradation and requiring a large number of particles to ensure accuracy. Biota intelligence algorithms led by Cuckoo (CS) and Firefly (FA) have achieved certain results after introducing particle filtering, respectively. This paper respectively in the two kinds of bionic algorithm convergence factor and adaptive step length and random mobile innovation, seized the cuckoo algorithm (CS) in the construction of the initial value and the firefly algorithm (FA) in the iteration convergence advantages, using the improved after the update mechanism of cuckoo algorithm optimizing the initial population, and will be updated after optimization way of firefly algorithm combined with particle filter. Experimental results show that this method can ensure the diversity of particles and greatly reduce the number of particles needed for prediction while improving the filtering accuracy.
