最新刊期
卷 39 ， 期 9 ， 2023
- 摘要：The 6G system will realize diversified and customized on-demand network services for thousands of industries.End-to-end network slicing can provide users with on-demand and flexible service guarantees.However, the existing network service orchestration and control based on network slicing has problems such as high manual participation, high configuration complexity, and high operation and maintenance cost.Therefore, a solution is urgently needed to meet these challenges.Intent-driven network has the characteristics of flexible reconfiguration and adaptive policy optimization, which can improve the user’s end-to-end service experience.An intent-driven end-to-end network slicing orchestration and control system architecture was proposed, which consisted of business application layer, intent-enabled layer and infrastructure layer.On this basis, the intent parsing module, orchestration and control module were designed.Furthermore, a utility evaluation model was constructed from the perspectives of user satisfaction and system intelligence, and system utility was evaluated through simulation.关键词：intent-driven network;end-to-end network slicing;orchestration and control;utility evaluation839|1154|0更新时间：2024-06-05
- 摘要：To effectively support the development needs of the deep integration of networking and computing, a novel computing and network convergence architecture has emerged.In this context, how to realize the intelligent perception of computing and networking resources and the efficient scheduling of computational tasks are key problems.To this end, the new network scenario for computing and networking convergence were analyzed, a scheduling model for computing tasks and nodes was designed, and a deep reinforcement learning-based resource scheduling algorithm was proposed.The proposed algorithm was able to intelligently make scheduling decisions that minimize the system cost by sensing key information such as user devices, available capacity of computing and networking resources, and link status.Finally, the effectiveness of the proposed algorithm in saving system cost was verified by simulation experiments.关键词：computing and network convergence;resource scheduling;deep reinforcement learning836|1305|0更新时间：2024-06-05
- 摘要：IP network expansion is a common maintenance method for communication operators to keep the network running smoothly.The core is to predict the network traffic trend in the future period.IP network traffic is very complex, with local uncertainty, burstiness, heterogeneity, etc., which brings difficulties to prediction.A prediction method for complex network traffic was proposed.It adopted an encode-decode structure, adding global features to the encoding layer, and combining global features and local features in the decoding layer to solve local uncertainties.The model used sample balance, normalization and other methods to extract the commonality of the data as much as possible to avoid the heterogeneity of the data.And emergencies were alleviated by increasing prior knowledge.The overall model had fewer parameters and had strong generalization performance, at the same time, the combination of artificial features and automatic features ensured the accuracy of the shallow network.The experimental results show that the proposed method has the characteristics of high accuracy and strong generalization performance.At present, this method has been applied on a large scale in engineering.关键词：network traffic prediction;IP network expansion;complex network traffic388|743|0更新时间：2024-06-05
- 摘要：Artificial intelligence generated content (AIGC) generated text itself carried moral and legal compliance risks, and the circulation of generated text content need to be regulated.Therefore, there was an urgent need for copyright protection of AIGC generated text.Watermarking technology was currently the most widely used method for digital copyright protection.A watermark embedding technology was proposed for generating text using generative causal language models.An in-process watermark embedding method was adopted, which implicitly embeded text watermark during the text generation process.Compared to traditional post-process watermark embedding technology, it had less impact on the quality of generated text and had advantages such as low perception, transparency, and robustness.The proposed method has low coupling with existing models and can eliminate the need to adjust the original model structure, training strategies, deployment methods, and increase the computational cost of the original generation process.Through experimental results, the proposed watermark embedding strategy has good robustness and can effectively detect text embedded watermarks even after a certain degree of editing by users.关键词：AIGC;generated causal language model;digital watermark;digital copyright458|1108|0更新时间：2024-06-05
- 摘要：The JiuTian intelligent network simulation platform was proposed, which could provide wireless communication simulation data services for the open innovation platform.The platform contained a series of scalable simulator functionalities, offering open services that enable users to use reinforcement learning algorithms for model training and inference based on simulation environments and data.Additionally, it allowed users to address optimization tasks in different scenarios by uploading and updating parameter configurations.The platform and its open services were primarily introduced from the perspectives of background, overall architecture, simulator, business scenarios, and future directions.关键词：simulation platform;emulator;business scenario;wireless communication;network intelligence450|1536|0更新时间：2024-06-05
- 摘要：As a future-oriented new network architecture, the core idea of computing and network convergence is to manage cloud-edge-end computing network resources in a centralized or distributed way by centering on the deep integration of computing force and network resources, so as to provide computing service for users’ needs.Although the CNC has made some progress in standard setting and industrial promotion, the overall development still faces many challenges, and there are still many scientific and engineering problems to be broken through.Research on CNC and its brain was carried out, the latest progress in related fields in the industry was analyzed, and the idea of building intelligent CNC brain was put forward, hoping to throw a brick at the table, jointly promote the implementation of AI in CNC, and truly realize intelligent CNC.关键词：computing and network convergence;CNC brain;intelligence;policy making303|480|0更新时间：2024-06-05
- 摘要：Autonomous networks achieve network self management, self optimization, and self repair by building intelligent network infrastructure.Autonomous network was divided into two key stages: AI model building and AI model deployment.However, the industry paid less attention to AI model deployment.The deployment phase of autonomous networks was systematically studied.Firstly, it elaborated on the independent deployment mode and full stack deployment mode of autonomous networks, and pointed out that full stack deployment was the main direction.Secondly, a detailed introduction was given to the full stack architecture with “five layers, dual domains, and four closed-loops”, which achieved full life cycle intelligence through a layered closed-loop design of resources and processes.Then, three core technologies for independent innovation were proposed: AI model training and inference integration to achieve rapid iterative updates of models, AI fabric technology to achieve customized application by rapid construction, and AI model cloud-edge collaborative deployment technology to achieve efficient application.Finally, the effectiveness of these three core technologies was verified through cases such as anomaly detection, smart telecommunication rooms, and equipment inspections.The deployment of autonomous networks was systematically explored, especially in terms of architecture design and core technology innovation, which had important reference value for telecommunication operators’ network digital transformation.关键词：autonomous network;full stack deployment;training and inference integration;cloud edge collaborative deployment;AI fabric338|1149|0更新时间：2024-06-05
Network Intelligence and Artificial Intelligence Generated Content
- 摘要：In recent years, 5G has been commercialized around the world in a large scale.However, considering the cost and geographical restrictions, traditional 5G networks still have trouble in providing seamless global communication.To reach the global area coverage, satellite and 5G technology integration has become a new hot topic in the communication industry.In 3GPP, the first release of 5G NTN technical specifications based on transparent payload architecture has been completed.Firstly, the standardization status of 5G NTN network architecture was introduced.Secondly, the shortcomings or issues existing in the current network architecture of 5G NTN were analyzed.Finally, three 5G NTN network architecture enhancement and optimization schemes were proposed, which including IAB-based network architecture, NTN adaptive network architecture and NTN multi-connection network architecture for intersatellite link construction and data shunt.The proposed architectures aim to providing valuable suggestions and references for the subsequent research, standardization and network deployment of 5G NTN.关键词：5G;NTN;network architecture;3GPP488|685|0更新时间：2024-06-05
Communication Standard
- 摘要：Extra-large scale MIMO (XL-MIMO) can meet the requirement of high spectral efficiency in 6G communication, but also faces the challenge caused by the increase in computational complexity.It is found that the unique spatial non-stationary characteristics of XL-MIMO channel brings new possibilities for low-complexity wireless transmission design.Firstly, starting from the near-field propagation effect, the research results of XL-MIMO channel characteristics analysis and channel modeling were combed, and the causes of spatial non-stationarity were deeply discussed.Furthermore, the concept of array visibility region (VR) in XL-MIMO was introduced, and the low-complexity wireless transmission design combined with VR information was discussed.Then, from the perspective of sub-array partition and distributed signal processing, the implementation of XL-MIMO low-complexity system architecture was introduced, and the corresponding design schemes were summarized.Finally, the future research direction was prospected.关键词：XL-MIMO;spatial non-stationarity characteristics;near field effect;visibility region;6G372|1036|0更新时间：2024-06-05
- 摘要：Aiming at the problem that the traffic flow prediction model did not consider the correlation of road context and the dynamics of spatial dependency, a multi-channel spatial-temporal traffic flow prediction based on hybrid static-dynamic graph convolution (MHGCN) was proposed.A sandwich structure (i.e.multi-channel spatial module in the middle and temporal module on both sides) was used in the model to extract spatial-temporal features, and the multi-channel spatial module was divided into static graph convolution module and dynamic graph convolution module.The static graph convolution module simultaneously extracted specific and common features from topological spatial structures, semantic spatial structures, and their combinations.The dynamic graph convolution module assigned different weights to different features and extracts dynamic spatial features from unknown graph structures.In the temporal module, the multi-head attention mechanism was used to extract the global temporal features, and the temporal gating mechanism extracted the local temporal features.The model extracted spatial information from different spatial structures and temporal information from different time intervals to establish a global and comprehensive spatial-temporal relationship.The experimental results show that the MHGCN performs better than the existing traffic flow prediction models on four real world traffic flow datasets.关键词：The National Natural Science Foundation of China;The “Pioneer” and “Leading Goose” Research ＆ Development Program of Zhejiang Province;intelligent transportation;dynamic graph convolution;multi-head attention344|869|0更新时间：2024-06-05
- 摘要：Geographical information extracted from social media text reveals underlying spatial correlations.A geographical location prediction method for social media text based on multimodal fusion was proposed.By utilizing images associated with the text as augmented data, an integrated image-text dataset was constructed to enhance the accuracy of geographical location prediction.The multimodal fusion model employs separate channels for images and text to independently extract their respective geographical location information.Additionally, a text-image matching module was introduced to denoise the image-text pairs, effectively solving the issue of text-image misalignment.Experimental results on the Geotext dataset indicate that compared to the baseline model, the proposed method reduces the median error distance by 18.8% and the average error distance by 4.5%.关键词：social media;geolocation;multimodal fusion;information mining225|558|0更新时间：2024-06-05
- 摘要：Communication and navigation symbiosis refers to the coexistence of these signals in the satellite ecological environment.For single-function low-orbit satellite constellations for positioning or communication, it is difficult to quickly perform positioning management when positioning or communication signals are unavailable.The extended Kalman filter (EKF) algorithm was proposed to solve the location of the opportunity signals of LEO communication navigation symbiosis constellations, breaking through the dependence of location management on a single navigation system.Firstly, the basic principle of Kalman filter was introduced, and a Kalman filter location management algorithm based on opportunity signal combining with the positioning management algorithm of LEO satellite constellation was proposed.Secondly, the advantages of this algorithm were analyzed, including improving positioning accuracy, improving positioning efficiency, improving positioning stability, etc.Finally, experiments were carried out to verify the effectiveness of the algorithm.The results show that the algorithm can effectively improve the positioning accuracy, efficiency and stability, and provides an effective solution for LEO communication navigation symbiosis constellation location management.关键词：global navigation satellite system;communication and navigation symbiosis;location management;signal of opportunity;power spectral density;inertial-navigation system;extended Kalman filter286|611|0更新时间：2024-06-05
- 摘要：The identification of the risk of network behavior victimization was of great significance for the prevention and warning of telecom network fraud.Insufficient mining of network behavior features and difficulty in determining relationships, an integrated optimization model for network behavior victimization identification based on association rule feature extraction was proposed.The interactive traffic data packets generated when users accessed websites were captured by the model, and the implicit and explicit behavior features in network traffic were extracted.Then, the association rules between features were mined, and the feature sequences were reconstructed using the FP-Growth algorithm.Finally, an analysis model of telecom network fraud victimization based on network traffic analysis was established, combined with the stochastic forest algorithm of particle swarm optimization.The experiments show that compared with general binary classification models, the proposed model has better precision and recall rates and can effectively improve the accuracy of network fraud victimization identification.关键词：The National Social Science Foundation of China;Zhejiang Natural Science Foundation and Public Welfare Research Program;Ministry of Public Security Science and Technology Plan Project;network traffic analysis182|546|0更新时间：2024-06-05
Research and Development
- 摘要：The evolution of customer service platforms was reviewed systematically, covering the first generation of interactive voice response (IVR) customer service, the second generation of multimedia online customer service, and the third generation of artificial intelligence (AI) customer service.The functional characteristics of each generation of customer service platforms were elaborated in depth.Additionally, the functional construction of customer service systems in various industries was introduced in detail, such as manufacturing, finance, transportation, and telecommunications.Based on this, the application components of AI customer service platforms for operators were further depicted, including intelligent dispatching, voice transcription, knowledge recommendation, intelligent quality inspection, and intelligent liability determination.Currently, the adoption of AI customer service platforms by operators has become a development trend.Looking forward, customer service platforms will integrate various intelligent technologies such as large-scale models, natural language processing (NLP), and knowledge graphs to meet customer service demands.关键词：AI customer service;customer service system;AI897|1842|0更新时间：2024-06-05
- 摘要：The deep cloud-network integration hopes that the network side can provide fine-grained and on-demand customized services for cloud-side services, which poses a great challenge to existing IP bearer networks.To this end, an architecture of database-based open resource service networking was proposed.By abstracting the atomic service capabilities of the network and publishing services through a strongly consistent distributed key-value database, on-demand use of networking services at the cloud-side, joint cloud-network orchestration, and one point of business access could be achieved, which could flexibly meet the needs of cloud-network integration and achieve efficient carrying and refined services for diversified businesses.关键词：network framework;open resource service;database199|259|0更新时间：2024-06-05
- 摘要：The 5G cellular network not only provides wireless communication capabilities for terminals but also offers positioning functionalities.Firstly, the 3GPP 5G positioning technology was briefly outlined, followed by the proposal of the 5G indoor positioning technology road-map.The cloud-edge collaborative integrated positioning architecture, the 5G+X fusion positioning solution, as well as the 5G positioning solution for smart parks were included, with a detailed analysis of the architecture and process.These positioning solutions seamlessly addressed the issue of locating people or objects in areas where GNSS signals cannot reach, which could meet the positioning accuracy and timeliness requirements in different scenarios.The technology solution has been applied in the industry with meter-level positioning accuracy and second-level timeliness, which has been well evaluated by customers.关键词：China Unicom Core Technology Research Project;5G;indoor positioning;fusion positioning518|1414|0更新时间：2024-06-05
Engineering and Application
- Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
- Total Visits：1034978 Visits Today：3027
0