Search

As an important bearer network of the fifth generation (5G) mobile communication technology, the optical transport network (OTN) needs to have high-quality network performance and management capabilities. Proof by facts, the combination of artificial intelligence (AI) technology and software-defined networking (SDN) can improve significant optimization effects and management for optical transport networks. However, how to properly deploy AI in optical networks is still an open issue. The training process of AI models depends on a large amount of computing resources and training data, which undoubtedly increases the carrying burden and operating costs of the centralized network controller. With the continuous upgrading of functions and performance, small AI-based chips can be used in optical networks as on-board AI. The emergence of edge computing technology can effectively relieve the computation load of network controllers and provide high-quality AI-based networks optimization functions. In this paper, we describe an architecture called self-optimizing optical network (SOON) with cloud-edge collaboration, which introduces control-layer AI and on-board AI to achieve intelligent network management. In addition, this paper introduces several cloud-edge collaborative strategies and reviews some AI-based network optimization applications to improve the overall network performance.

A traffic scheduling strategy based on edge coordination is proposed to mitigate DDoS attacks for edge nodes in TWDM-PON. Results reveal that our proposed algorithm effectively reduces service blocking and QoS degradation caused by DDoS.

Industrial control systems(ICS) are widely used in national infrastructure such as electricity, water conservancy and energy to control the operation of production equipment. The ICS information security problems will cause a series of consequences. This paper focuses on the security problems existing in industrial communication protocols, studies the secure protocols to guarantee the secure transmission of industrial datas, and realizes the end-to-end identity authentication and data encryption transmission on Modbus/TCP protocol.

A DNN model partition and deployment algorithm is proposed between edge nodes and cloud in metro optical network. Simulation results show that the algorithm can deploy more DNN tasks with the same network resource.

As the significant infrastructure of the communication network, the security of the optical fiber is critical. Optical fiber eavesdropping is a common attack in optical communications, which can easily lead to leakage of information. To deal with this problem, this paper proposes a Machine Learning (ML)-based scheme to detect and locate physical-layer eavesdropping. To improve the efficiency and accuracy of eavesdropping detection, both Optical Performance Monitoring (OPM) data and eye-diagrams are adopted as input data. Three different ML classifiers are designed and tested to realize eavesdropping detection, location and split ratio recognition, respectively. To demonstrate the feasibility of the proposed scheme, an experiment is conducted in end-to-end fiber transmission system with Coherent Optical Orthogonal Frequency Division Multiplexing (CO-OFDM). The eavesdropping is simulated and performed by placing optical coupler in different positions. In addition, different splitting ratios are considered, including 95/5, 90/10. Results indicate that the ML scheme achieves 100% and 92.76% accuracy in eavesdropping detection and location, respectively.

A color image encryption algorithm using the Henon-zigzag map and chaotic restricted Boltzmann machine (CRBM) is proposed in this paper. The proposed pseudo-random number generator, chaotic restricted Boltzmann machine (CRBM), can simultaneously generate three pseudo-random number sequences. The algorithm includes the permutation phase and the diffusion phase. In the Henon-zigzag map-based permutation phase, zigzag map is used to modulate two pseudo-random number sequences generated by Henon map to obtain two new pseudo-random number sequences. The mixing of these two chaotic maps makes the security of the permutation phase significantly improve. Subsequently the two pseudo-random number sequences are used for row permutation and column permutation, respectively. In the diffusion phase, through multiple iterations of CRBM of the 3 × 3 architecture, three pseudo-random number sequences are generated by the state values of three neurons in the visible layer. Then these three pseudo-random number sequences are used for bitxor operation with the R, G and B components of the scrambled image, respectively. A series of numerical experiments and analyses on encrypted images prove that the proposed algorithm is more secure than state-of-the-art algorithms. Furthermore, based on the combined use of blockchain and the proposed algorithm, a novel image encryption/decryption system is proposed. The system has two features: asymmetric encryption/decryption of images and authoritative verification of the integrity of encrypted images. It may provide a better understanding of blockchain in digital image encryption.

According to complex equipment's characteristics, the article divides tasks, analyzes task objects' relationship, proposes successful task criteria and builds a task model. This process becomes an important part of complex equipment RMS (reliability, maintainability, supportability) model after fully consideration of the cooperatively between multiple equipment. Finally, the article shows modelling process and verifies method by example which uses a typical combat mission.

Generally the application of traditional adaptive control algorithm relies on the mathematic model of system. But mathematic models of some dynamic systems are difficult to establish. According to this actual problem and the existing structure of algorithm, an improved Model Free Adaptive control algorithm based on neural network is put forward in this paper. Within corresponding controller, equivalent proportion link is used to enhance the flexibility of adjustable parameters and speed, in addition, the estimate of sensitivity of process is used to update the values of the weighting factors, which can improve the actual application effect of neural network. In the end, simulation result shows that this algorithm can get the good performance in the aspect of stability, speed and adaptability.