最新刊期
卷 40 ， 期 5 ， 2024
- 摘要：At present, the society is in an era of rapid development of science and technology, and the rapid development of wireless communication technology has not only promoted the digital transformation of industry, transportation, medical and other fields, but also continuously upgraded wireless communication networks, trying to move from wired to wireless. With the continuous evolution of computer technology and wireless communication technology, many application scenarios require highly reliable transmission in a wireless environment. Especially in the fields of modern industrial automation and autonomous driving, the demand for highly reliable transmission is more urgent. 5G technology was delved into, which was one of the most advanced wireless transmission technologies in the industry, focusing on multi-channel redundant transmission technology within 5G systems. The key points of the technology in terms of application background, technical principles and technical route were summarized. In terms of application background, the practical application requirements of 5G redundant transmission in wireless scenarios such as modern industrial automation and autonomous driving were highlighted. In terms of technical principles, the relevant research was summarized and sorted out from the end-to-end multi-channel redundant transmission of services, the analysis of the technical principles of 5G multi-channel redundant transmission were focused on, and its unique advantages in improving transmission reliability were explained. In terms of technical routes, the development direction of 5G multi-channel redundant transmission technology and various possible implementation paths were comprehensively considered. Finally, the difficulties and challenges of the future development of 5G multi-channel redundant transmission technology were pointed out, and its future development trend was discussed, so as to better understand the key role and prospect of 5G redundant transmission technology in the field of wireless communication.关键词：5G;URLLC;multi-redundant transmission;copy and eliminate;deterministic969|2203|0更新时间：2024-08-05
- 摘要：With the large-scale commercial use of the global 5G network and the rapid growth of mobile Internet traffic, more abundant wireless spectrum resources can be released, and the demand for high-speed optical modules in wireless front-haul networks is increasingly prominent. Focusing on the key technologies of 50 Gbit/s front-haul optical modules, two main networking methods were deeply analyzed, the typical transmission distance and link loss were analyzed, the maximum and minimum dispersion values of coarse wave division multiplexing (CWDM) wavelengths in a 10 km scenario were explored, and the corresponding dispersion compensation strategies were studied. Through experiments, the changes in optical power penalty of different multi-path interference (MPI) were verified, and the potential impact of MPI noise on error performance was analyzed in detail. In addition, deep research on the optoelectronic chip scheme of 50 Gbit/s modules was conducted, the parameters of various types of optical modules were rigorously tested, standardized suggestions for the optoelectronic interface parameters of 50 Gbit/s front-haul modules were proposed, the current standard status of 50 Gbit/s modules at home and abroad was detailed, and the development trend of future applications was prospected.关键词：5G network;50 Gbit/s front-haul optical module;dispersion;multi-path interference;optoelectronic interface parameter455|598|0更新时间：2024-08-05
Review
- 摘要：In addressing the challenge of the multiplicative fading introduced by passive reconfigurable intelligent surface (RIS) in high-speed railway scenarios, an effective solution is the deployment of an active RIS. However, the conventional fully-connected architecture of active RIS, characterized by a multitude of active elements, results in excessive hardware costs and power consumption. Consequently, a sub-connected architecture of active RIS was proposed, with the aim of simultaneously considering the system's energy efficiency and the transmission rate in train-ground communication. Initially, a system model for active RIS-assisted multi-user scenarios was established, taking into account the distinctive features of the high-speed railway environment. Subsequently, the problem of maximizing system energy efficiency was formulated by considering constraints on the maximum transmission power of the base station, the transmission power of the active RIS, and the phase-shift matrix of the active RIS. Through the utilization of Lagrange dual transformation and quadratic transformation from fractional programming theory, the non-convex problem was transformed into a convex optimization problem. Finally, an alternating optimization algorithm was proposed for the joint optimization of beamforming and the phase-shift matrix of the active RIS. Simulation results indicate that, compared to traditional passive RIS and fully-connected of active RIS architectures, the proposed solution effectively addresses the multiplicative fading issue. Additionally, the proposed solution achieves higher energy efficiency while meeting user transmission rate requirements.关键词：high-speed railway;reconfigurable intelligent surface;sub-connected structure;beamforming;energy efficiency393|303|0更新时间：2024-08-05
- 摘要：A frame synchronization algorithm based on delay-Doppler domain was proposed for orthogonal time frequency and space (OTFS) modulation systems with a single pilot structure. The signal sparsity and the relative position change of the pilot in the delay-Doppler domain of the received OTFS signals were utilized to identify the frame synchronization location. Simulation results were presented to demonstrate that the proposed scheme outperformed the classic synchronization scheme based on the preamble, which was commonly used in orthogonal frequency division multiplexing (OFDM) systems, in terms of lower synchronization failure rate under high signal-to-noise ratio (SNR) regions. Additionally, the proposed scheme exhibited greater performance advantages over the preamble-based scheme as the moving speed increases, making it a more suitable option for high-speed or even ultra-high-speed mobile communication scenarios.关键词：OTFS modulation;single pilot structure;sparsity;frame synchronization189|916|0更新时间：2024-08-05
- 摘要：A fusion algorithm named permutation entropy weighted and bias adjustment rule fusion (PEW-BAR) was proposed to enhance the accuracy of speech emotion recognition by exploiting the emotional information in the spectral characteristics of speech signals. The algorithm was based on the integration of wavelet scattering transform and Mel-frequency cepstral coefficients (MFCC). Firstly, wavelet scattering features and MFCC-related features from speech signals were extracted. Then, the wavelet scattering features were expanded in the scale dimension and applied support vector machines to obtain posterior probabilities for emotion recognition. And permutation entropy was calculated and a weighted fusion based on this entropy was subsequently applied. Finally, a bias adjustment rule was utilized to refine the integration results obtained from the MFCC-related features. Experimental results on various datasets, including EMODB, RAVDESS, and eNTERFACE05, demonstrate notable improvements. The proposed algorithm outperforms traditional wavelet scattering coefficient-based methods, achieving accuracy improvements of 2.82%, 2.85%, and 5.92%, respectively. Additionally, it shows enhancements of 3.40%, 2.87%, and 5.80% in terms of unweighted average recall (UAR), and a 6.89% improvement on the IEMOCAP dataset.关键词：speech emotion recognition;wavelet scattering transform;permutation entropy;MFCC;model fusion85|403|0更新时间：2024-08-05
- 摘要：Aiming at the challenges associates with the low quality and structural errors existed in the images generated by a single text description, a multi-stage generative adversarial network model was used to study, and it was proposed to interpolate different text sequences to enrich the given text descriptions by extracting features from multiple text descriptions and imparting greater detail to the generated images. In order to enhance the correlation between the generated images and the corresponding text, a multi-captions deep attentional multi-modal similarity model that captured attention features was introduced. These features were subsequently integrated with visual features from the preceding layer, serving as input for the subsequent layer. This integration improved the realism of the generated images and enhanced their semantic consistency with the text descriptions. In addition, a self-attention mechanism to enable the model to effectively coordinate the details at each position was incorporated, resulting in images that were more aligned with real-world scenarios. The optimized model was verified on the CUB and MS-COCO datasets, demonstrating the generation of images with intact structures, stronger semantic consistency, and richer visual diversity.关键词：text-to-image;generative adversarial network;computer vision;semantic consistency;self-attention288|522|0更新时间：2024-08-05
- 摘要：In response to the diverse business needs of the future in all domains and scenarios, 6G networks need to provide scenario-based and personalized service capabilities. Aiming at the problem of quality assurance of fine-grained business services in the future, a joint optimization algorithm for 6G network task offloading and fine-grained slice resource scheduling was proposed, which jointly considered the calculation offloading of multiple MECs and the resource scheduling of network slices, and minimized the execution delay and energy consumption cost of the task within limited resources. Then the A3C reinforcement learning algorithm of asynchronous training was used to solve it. The simulation results show that, compared with the traditional algorithm, the proposed algorithm can reduce the computing cost while meeting the business needs of users. Additionally, the algorithm converges fast and can realize fast decision-making.关键词：6G network;task offloading;fine-grained slicing;multi-dimensional resource;joint optimization135|334|0更新时间：2024-08-05
- 摘要：The research on emotion recognition in conversations (ERC) focuses on the interrelationship between conversational context and speaker modeling. The current research usually ignores the dependency within the conversation, which leads to the weak connection between the context of the conversation and the lack of logic between the speakers. Therefore, an emotion recognition in conversations model based on discourse parsing and graph attention network (DPGAT) was proposed to integrate the inter-dependency of conversation into the context modeling to make contextual information more dependent and global. Firstly, the discourse dependency relationships within the conversation were obtained through discourse parsing, and the discourse dependency graph and the speaker relationship graph were constructed. Subsequently, different types of speaker diagrams were internally integrated by multi-head attention mechanisms. Based on the graph attention network, cyclic learning was combined with dependency relationships to achieve the effective integration of contextual information and speaker information, realizing the external integration of context-related information in conversations. Finally, by analyzing the results of internal and external integration, the complete conversation context was restored, and the speaker's emotions were analyzed. By evaluating and verifying on English dataset MELD, EmoryNLP, DailyDialog and Chinese dataset M3ED, F1 scores were 66.23%, 40.03%, 59.28% and 52.77%, respectively. Compared with mainstream models, the proposed model at least reaches state-of-the-art, and can be used in different language scenarios.关键词：emotion recognition in conversations;discourse parsing;graph attention network131|826|0更新时间：2024-08-05
- 摘要：Cognitive radio non-orthogonal multiple access (CR-NOMA) technology was used to alleviate the shortage of spectrum resource, and improve the throughput of sensor devices. But the energy efficiency problem had been restricting the application of sensor devices. Therefore, for CR-NOMA, deep deterministic policy gradient-based energy efficiency optimization (DPEE) algorithm was proposed. By jointly optimizing the transmission power and time slot splitting coefficient, the energy efficiency of sensor devices was improved. The energy efficiency optimization problem was modeled as a Markov decision process, and it was solved by the deep deterministic policy gradient (DDPG) method. Finally, the influence of circuit power consumption, time slot durations and number of main devices on energy efficiency were analyzed. The simulation results show that the energy efficiency decreases as the circuit power consumption of sensor device increases. In addition, compared with other algorithms, the proposed algorithm improves energy efficiency.关键词：sensor device;energy harvesting;cognitive radio non-orthogonal multiple access;energy efficiency;deep deterministic policy gradient78|284|0更新时间：2024-08-05
- 摘要：The bidirectional DC-DC converter was selected as the research object. Based on the connection topology of energy storage and consumption components in the hybrid energy storage system, power demand indicators were determined for different energy flow directions, and the parameters of the main converter components and appropriate circuit components were established. A circuit model of buck/boost was constructed, and an adaptive fast terminal sliding mode control strategy was designed. The controller parameters were optimized using an improved genetic algorithm. Different control parameters have different control effects. In order to obtain better voltage output characteristics,the parameters of the adaptive fast terminal sliding mode control strategy were optimized.The proposed method can be verified to exhibit good control performance through simulation.关键词：genetic algorithm;BP neural network;self disturbance rejection;Cuk converter;DC-DC143|448|0更新时间：2024-08-05
- 摘要：With the development of the Chinese economy and the increasing pressure of living in first-tier cities, more and more young people choose to return to their hometowns for development. To efficiently serve users and improve their product usage experience, the use of algorithms such as LightGBM and CatBoost was proposed to predict the returning population, thereby providing a basis for services and products, and improving user market retention rates.关键词：LightGBM;feature engineering;KNN;K-fold cross-validation110|348|0更新时间：2024-08-05
Research and Development
- 摘要：China Telecom has launched a high-efficient and collaborative wide-area big data architecture system, the cloud edge computing big data platform, for large-scale governmental and enterprise organizations spanning multiple geographies and clusters. The platform logically abstracts data partitions through the cluster dimension, integrates multiple independent datasets into a "virtual dataset", and achieves many-to-one dataset mapping management. At the same time, the computing load dataset of the platform has generalized characteristics, which can flexibly cope with the data processing requirements in different scenarios. In addition, the platform also supports a variety of computing engines and scheduling systems using relational expressions as intermediate representations to achieve batch tasks for large-scale, complex data processing in highly fault-tolerant scenarios. At present, the cloud edge computing big data platform has been applied in a variety of application scenes. The platform has improved efficiency by 17% in 5G Core capacity scheduling subsystem (5GC) multi-centre big data job development and operation, and has achieved the collaborative scheduling of a total of 42 PB of storage, 84 TB of memory, and 24 984 VCore computing resources, with a daily average of 80 308 times of task scheduling between the front cluster and the core cluster.关键词：cloud edge collaboration;uniform SQL;task optimization;big data platform189|468|0更新时间：2024-08-05
- 摘要：In network service systems, the occurrence of anomaly events often leads to a large number of alarm events in the system, forming alarm storms. Operators need to spend a lot of time and effort searching for key information and identifying the root cause of anomaly events from these alarm data. In order to reduce the number of alarms that operators needed to handle, as well as automatically extracted the root alarms in the alarm storm, a method for generating an alarm causality graph based on the analysis of the propagation mode of network service alarms was proposed , and applied to extract key information of the alarm storm when anomaly events occurred. Real datasets of an operator's online network management system were used in experiments to verify the effect of building the alarm causal graph in extracting the alarm storm abstract. A real-world case was used to analyze the physical significance of this method. The results show that the recall rate of extracting alarm storm summary can reach 96% and the vast majority of key information is retained by using the method of alarm causality graph generation. In addition, the compression rate of alarms using this method can reach 66.5% for alarm codes that are difficult to compress.关键词：alarm compression;anomaly event;alarm storm summary;causality graph;artificial intelligence for IT operations95|257|0更新时间：2024-08-05
- 摘要：The dedicated network of the Jiangsu Provincial Department of Ecology and Environment is in need of upgrades and transformation. A project team was established to conduct extensive research and analysis on technical systems. After a lot of technical system demonstration and research work, it was decided that the upgrade and transformation should be based on software-defined wide area network (SDWAN) technology. An overview of the current state of the dedicated network was proposed, a needs analysis was conducted, and a technical solution was proposed to meet the requirements of the upgrade. The proposed solution includes overall solution design, SDWAN solution design, security protection design, and network management design.关键词：SDWAN;security protection;network management226|466|0更新时间：2024-08-05
- 摘要：With the upgrading of China's digital strategy, various industries have gradually entered the deep water of digital transformation. Focusing on the "industrial digitalization platform infrastructure" as the research area and aiming at the "digital transformation of operator industry" ,the current situation and future development trends of digital transformation in the operator industry during the digital era were reviewed. And starting from the actual situation of telecom operators, the current situation and practical shortcomings of the industrial digitalization platforms were analyzed, and the expectations for the practical innovation of the operator industry digitalization platform in the future were proposed.关键词：industry digitization;infrastructure;operator100|375|0更新时间：2024-08-05
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：1035510 Visits Today：3559
0