A5091039444- Advanced Optical Network Technologies
- Advanced Photonic Communication Systems
- Optical Network Technologies
- Software-Defined Networks and 5G
- Network Security and Intrusion Detection
- Network Traffic and Congestion Control
- Cooperative Communication and Network Coding
- Internet Traffic Analysis and Secure E-voting
- IoT and Edge/Fog Computing
- Air Quality Monitoring and Forecasting
- Interconnection Networks and Systems
- Complex Network Analysis Techniques
- Photonic and Optical Devices
- Satellite Communication Systems
- Neural Networks and Reservoir Computing
- Full-Duplex Wireless Communications
- Network Packet Processing and Optimization
- Peer-to-Peer Network Technologies
- Video Surveillance and Tracking Methods
- Air Quality and Health Impacts
- Cloud Computing and Resource Management
- Wireless Networks and Protocols
- Advanced Computing and Algorithms
- Semiconductor Lasers and Optical Devices
- Advanced MIMO Systems Optimization
Beijing University of Posts and Telecommunications
2016-2025
State Key Laboratory of Information Photonics and Optical Communications
2013-2024
Beijing University of Technology
2016-2018
Beijing Advanced Sciences and Innovation Center
2016
The evolution toward 5G mobile networks is characterized by supporting higher data rate, excellent end-to-end performance and ubiquitous user-coverage with lower latency, power consumption, cost. To support this, the RANs are evolving in two important aspects. One aspect “cloudification,” which to pool baseband units be centralized for statistical multiplexing gain. other use advanced optical technologies digital analog signal transmission a cloud-based RAN. In this article, we focus on BBU...
Increasingly, more people are suffering from the effects of air pollution. This study took Beijing as an example and proposed attention-based quality predictor (AAQP) that could better protect The AAQP is a seq2seq model, it exploits historical data weather to predict future indexes. Although existing research has promoted for prediction, there still two problems. First, slow training speed so original RNN in encoder was replaced with fully connected accelerate process. Position embedding...
Network virtualization is meant to improve the efficiency of network infrastructure by sharing a physical substrate among multiple virtual networks. Virtual embedding (VNE) determines how map request onto substrate. In this paper, we first overview three possible underlying substrates for interdatacenter networks, namely an electrical-layer-based substrate, optical-layer-based and multilayer-based (optical electrical layer) Then, corresponding VNE problems are discussed. The work presented...
The wide coverage of satellite networks and the large bandwidth terrestrial have led to an increasing research on integration two (ISTN) for complementary advantages. However, most researches routing mainly focus internal network. Due point-to-area channel characteristics between satellites ground stations, heterogeneity ISTN has increased, which makes that algorithm traditional cannot be applied end-to-end ISTN. Meanwhile, data flows with elastic quality service attribute make pre-assign...
This letter proposes a new scheme that uses Reward Function Learning for Q-learning-based Geographic routing (RFLQGeo) to improve the performance and efficiency of unmanned robotic networks (URNs). High mobility nodes changing environments pose challenges geographic protocols; with multiple features simultaneously considered, becomes even harder. protocols (QGeo) preconfigured reward function encumber learning process increase network communication overhead. To solve these problems, we...
The rapid evolution of data transmission has posed unprecedented challenges to the dynamic resource provisioning in optical networks. In this letter, we investigate spectrum defragmentation problem elastic networks, and propose a novel deep reinforcement learning based solution Deep-DF achieve self-adaptive optimization. Compared existing pre-fixed heuristics tailored only immediate optimizations for current network state, key advantage is that it can be trained identify perform hitless...
We propose a proactive dynamic network slicing scheme that utilizes deep-learning based short-term traffic prediction approach for 5G transport networks. The demonstration shows utilization efficiency improvement from 46.33% to 71.53% under the evaluated scenario.
Atmospheric visibility is an indicator of atmospheric transparency and its range directly reflects the quality environment. With acceleration industrialization urbanization, natural environment has suffered some damages. In recent decades, level shows overall downward trend. A decrease in will lead to a higher frequency haze, which seriously affect people's normal life, also have significant negative economic impact. The causal relationship mining can reveal potential relation between other...
We propose a hybrid quantum-classical computing mechanism with Coherent Ising Machine for dynamic QoT-aware RMSA in MB-FONs. The solution time is reduced from nearly 2 sec to 323 μs compared the auxiliary graph method.
We propose a GSNR-aware model with an optimization method based on it for multiband transmission system, improving mean value and flatness of GSNR by 1.08 dB 40.02 % across dynamic scenarios.
In the evolution of artificial Intelligence (AI) and machine learning (ML); reasoning, knowledge representation, planning, learning, natural language processing, perception, ability to move manipulate objects have been widely used. These features enable creation intelligent mechanisms for decision support overcome limits human processing. addition, ML algorithms applications draw conclusions make predictions based on existing data without supervision, leading quick near-optimal solutions...
The diagnosis of breast cancer in the middle and early period is conducive to later treatment, but current rate not very desirable. Using machine learning predict benign malignant can provide some assist doctors' treatment clinical practice. In this paper, we have collected data from digitized images a fine needle aspirate (FNA) mass. They describe characteristics cell nuclei presented image. This work adopts several feature selection methods select most related features for diagnosis. Based...
Recently, a cloud radio access network (C-RAN) has been proposed as candidate architecture for fifth-generation mobile communication. Fronthaul is new segment in C-RAN. In this paper, we investigate the algorithms resource allocation time and wavelength division multiplexing passive optical enabled fronthaul. We formulate an integer nonlinear programming (INLP) model, considering operation mode of small cell. A heuristic method also based on adaptive parallel genetic algorithm (GA). Three...