2023 Vol. 32, No. 6

SPECIAL FOCUS: ENABLING TECHNOLOGIES FOR VEHICLE-TO-EVERYTHING COMMUNICATIONS TOWARDS 6G ERA
A V2V Emergent Message Dissemination Scheme for 6G-Oriented Vehicular Networks
CHEN Chen, WANG Chenyu, CONG Li, XIAO Ming, PEI Qingqi
2023, 32(6): 1179-1191. doi: 10.23919/cje.2022.00.337
Abstract(905) HTML (451) PDF(323)
Abstract:
To ensure traffic safety and improve traffic efficiency, vehicular networks come up with multiple types of messages for safety and efficiency applications. In sixth-generation (6G) systems, these messages should be timely and error-free disseminated through vehicle-to-vehicle (V2V) communication to ensure traffic safety and efficiency. V2V supports direct communication between two vehicle user equipments, regardless of whether a base station is involved. We propose a packet delivery ratio (PDR)-based message dissemination scheme (PDR-MD) between V2V in 6G-oriented vehicular networks to select relay vehicles when broadcasting emergent messages. This scheme grasps the balance between vehicle distance and PDR so as to reduce transmission delay while ensuring reliable PDR. We compared the PDR-MD scheme with other probabilistic broadcasting schemes. The experimental results show that the PDR-MD protocol can maintain close to 95% and above PDR in transmitting emergent messages, and the transfer rate stays below 40%.
Mobility-Aware Multi-Task Migration and Offloading Scheme for Internet of Vehicles
LI Xujie, TANG Jing, XU Yuan, SUN Ying
2023, 32(6): 1192-1202. doi: 10.23919/cje.2022.00.333
Abstract(421) HTML (211) PDF(85)
Abstract:
In Internet of vehicles, vehicular edge computing (VEC) as a new paradigm can effectively accomplish various tasks. Due to limited computing resources of the roadside units (RSUs), computing ability of vehicles can be a powerful supplement to computing resources. Then the task to be processed in data center can be offloaded to the vehicles by the RSUs. Due to mobility of the vehicles, the tasks will be migrated among the RSUs. How to effectively offload multiple tasks to the vehicles for processing is a challenging problem. A mobility-aware multi-task migration and offloading scheme for Internet of vehicles is presented and analyzed. Considering the coupling between migration and offloading, the joint migration and offloading optimization problem is formulated. The problem is a NP-hard problem and it is very hard to be solved by the conventional methods. To tackle the difficult problem, the idea of alternating optimization and divide and conquer is introduced. The problem can be decoupled into two sub-problems: computing resource allocation problem and vehicle node selection problem. If the vehicle node selection is given, the problem can be solved based on Lagrange function. And if the allocation of computing resource is given, the problem turns into a 0-1 integer programming problem, and the linear relaxation of branch bound algorithm is introduced to solve it. Then the optimization value is obtained through continuous iteration. Simulation results show that the proposed algorithm can effectively improve system performance.
Multi-Objective Coordinated Optimization for UAV Charging Scheduling in Intelligent Aerial-Ground Perception Networks
ZHOU Yi, CHENG Xiang, SHI Huaguang, JIN Zhanqi, NING Nianwen, LIU Fuqiang
2023, 32(6): 1203-1217. doi: 10.23919/cje.2022.00.334
Abstract(631) HTML (312) PDF(111)
Abstract:
The unmanned aerial vehicles (UAVs)-assisted intelligent traffic perception system can provide effective situation awareness. However, UAVs are required to be recharged before the energy is exhausted, which may cause task interruption. To address this concern, the charging UAV (CUAV) is employed to provide wireless charging for the mission UAVs (MUAVs). This paper studies the charging scheduling problem of the CUAV under the premise of optimizing the MUAVs deployment. We first model the MUAVs deployment problem considering the energy consumption and data transmission and establish the CUAV charging model. Then, the above problem is formulated as a multi-objective multi-agent stochastic game process to simplify the decisions-making of MUAVs and CUAV, based on which we propose the utility-based Pareto optimal deployment and charging algorithm, which reduces the computing complexity by equivalent utility of the MUAVs while using Kullback-Leibler divergence to constrain solutions. Next, to ensure the effectiveness of policy update, the multi-agent communication protocol is adopted to improve policy exploration efficiency. Simulation results show that the proposed algorithm outperforms existing works in terms of energy efficiency and charging by comparing with the Pareto front of different methods, endurance anxiety of the MUAVs, and charging utilization under different task modes.
Collaborative Caching in Vehicular Edge Network Assisted by Cell-Free Massive MIMO
WANG Chaowei, WANG Ziye, XU Lexi, YU Xiaofei, ZHANG Zhi, WANG Weidong
2023, 32(6): 1218-1229. doi: 10.23919/cje.2022.00.294
Abstract(471) HTML (236) PDF(77)
Abstract:
The 6G mobile communications demand lower content delivery latency and higher quality of service for vehicular edge network. With the popularity of content-centric networks, mobile users are paying more and more attention to the delay and reliability of fetching cached content. For reducing communication costs, increasing network capacity and improving the content delivery, we propose a collaborative caching scheme based on deep reinforcement learning for vehicular edge network assisted by cell-free massive multiple-input multiple-output (MIMO) system, in which the macro base station is considered as the central processor unit, and the roadside units are treated as roadside access points (RSAPs). The proposed scheme can effectively cache contents in edge nodes, i.e., RSAPs and vehicles with caching capability. We jointly consider the mobility of vehicles and the content request preferences of users, then we use deep Q-networks algorithm to optimize the caching decisions. Simulation results show that the proposed scheme can significantly reduce the content delivery average latency and increase the content cache hit ratio.
Towards V2I Age-Aware Fairness Access: A DQN Based Intelligent Vehicular Node Training and Test Method
WU Qiong, SHI Shuai, WAN Ziyang, FAN Qiang, FAN Pingyi, ZHANG Cui
2023, 32(6): 1230-1244. doi: 10.23919/cje.2022.00.093
Abstract(888) HTML (441) PDF(87)
Abstract:
Vehicles on the road exchange data with base station frequently through vehicle to infrastructure (V2I) communications to ensure the normal use of vehicular applications, where the IEEE 802.11 distributed coordination function is employed to allocate a minimum contention window (MCW) for channel access. Each vehicle may change its MCW to achieve more access opportunities at the expense of others, which results in unfair communication performance. Moreover, the key access parameter MCW is privacy information and each vehicle is not willing to share it with other vehicles. In this uncertain setting, age of information (AoI), which measures the freshness of data and is closely related with fairness, has become an important communication metric. On this basis, we design an intelligent vehicular node to learn the dynamic environment and predict the optimal MCW, which can make the intelligent node achieve age fairness. In order to allocate the optimal MCW for the vehicular node, we employ a learning algorithm to make a desirable decision by learning from replay history data. In particular, the algorithm is proposed by extending the traditional deep-Q-learning (DQN) training and testing method. Finally, by comparing with other methods, it is proved that the proposed DQN method can significantly improve the age fairness of the intelligent node.
PLC for In-Vehicle Network: A DRL-Based Algorithm of Diversity Combination of OFDM Subcarriers
CHEN Zhixiong, ZHANG Zhikun, CAO Tianshu, ZHOU Zhenyu
2023, 32(6): 1245-1257. doi: 10.23919/cje.2022.00.331
Abstract(416) HTML (208) PDF(62)
Abstract:
For low latency communication service of vehicles, it is critical to improve the delay performance of power line communication (PLC) for in-vehicle network, which can decrease the weight and cost of the vehicle. In order to minimize the total time slots used in a transmission task, an orthogonal frequency-division multiplexing (OFDM) subcarrier diversity combination algorithm of PLC based on the deep reinforcement learning (DRL) is proposed herein. The short packet communication theory is used to develop an optimal combination model with constraints on short packet reliability, transmitting power and the amount of data. The state, action, and reward function of double deep Q-learning network (DDQN) are defined, and diversity combination for OFDM subcarriers is performed using DDQN. An adaptive power allocation algorithm based on the thresholds of error rate and the data amount is used. Simulation results show that the proposed algorithm can effectively improve the delay performance of PLC under the constraints of power and data amount.
Overlay CR-NOMA Assisted Intelligent Transportation System Networks with Imperfect SIC and CEEs
LI Xingwang, GAO Xuesong, LIU Yingting, HUANG Gaojian, ZENG Ming, QIAO Dawei
2023, 32(6): 1258-1270. doi: 10.23919/cje.2022.00.071
Abstract(1515) HTML (753) PDF(127)
Abstract:
With the development of the mobile communication and intelligent information technologies, the intelligent transportation systems driven by the sixth generation (6G) has many opportunities to achieve ultra-low latency and higher data transmission rate. Nonetheless, it also faces the great challenges of spectral resource shortage and large-scale connection. To solve the above problems, non-orthogonal multiple access (NOMA) and cognitive radio (CR) technologies have been proposed. In this regard, we study the reliable and ergodic performance of CR-NOMA assisted intelligent transportation system networks in the presence of imperfect successive interference cancellation (SIC) and non-ideal channel state information. Specifically, the analytical expressions of the outage probability (OP) and ergodic sum rate (ESR) are derived through a string of calculations. In order to gain more insights, the asymptotic expressions for OP and ESR at high signal-to-noise ratio (SNR) regimes are discussed. We verify the accuracy of the analysis by Monte Carlo simulations, and the results show: i) Imperfect SIC and channel estimation errors (CEEs) have negative impacts on the OP and ESR; ii) The OP decreases with the SNR increasing until convergence to a fixed constant at high SNR regions; iii) The ESR increases with increasing SNR and there exists a ceiling in the high SNR region.
CIRCUITS AND SYSTEMS
Circuit Modeling and Performance Analysis of GNR@SWCNT Bundle Interconnects
ZHAO Wensheng, YUAN Mengjiao, WANG Xiang, WANG Dawei
2023, 32(6): 1271-1277. doi: 10.23919/cje.2021.00.379
Abstract(490) HTML (244) PDF(58)
Abstract:
In this paper, the single-walled carbon nanotube (SWCNT) with graphene nanoribbon (GNR) inside, namely GNR@SWCNT, is proposed as alternative conductor material for the interconnect applications. The equivalent circuit model is established, and the circuit parameters extracted analytically. By virtue of the equivalent circuit model, the signal transmission performance of GNR@SWCNT bundle interconnect is evaluated and compared with its Cu and SWCNT counterparts. The optimal repeater insertions in global- and intermediate-level GNR@SWCNT bundle interconnect are studied. Moreover, it is demonstrated that the GNR@SWCNT interconnects could provide superior performance, indicating that GNR@SWCNT structure would be beneficial for development of future carbon-based integrated circuits and systems.
A Dynamic Hysteresis Model of Piezoelectric Ceramic Actuators
DONG Ruili, TAN Yonghong, XIE Yingjie, LI Xiaoli
2023, 32(6): 1278-1285. doi: 10.23919/cje.2021.00.273
Abstract(637) HTML (321) PDF(67)
Abstract:
A modified Prandtl-Ishlinskii (PI) model with rate-dependent thresholds for describing the hysteresis characteristics of piezoelectric actuators is proposed. Based on the classical PI model, a novel threshold depending on the input rate is constructed. With the novel rate-dependent threshold, the play operator has the capability to track the frequency variation of the input signal. Hence, the proposed modified PI model can be used to depict the rate-dependent hysteresis of piezoelectric actuators. Experimental results are presented to illustrate the model validation results of the proposed modeling.
Technology Dependency of TID Response for a Custom Bandgap Voltage Reference in 65 nm to 28 nm Bulk CMOS Technologies
LIANG Bin, WEN Yi, CHEN Jianjun, CHI Yaqing, YAO Xiaohu
2023, 32(6): 1286-1292. doi: 10.23919/cje.2021.00.448
Abstract(854) HTML (426) PDF(70)
Abstract:
Total ionizing dose (TID) radiation response of the custom bandgap voltage reference (BGR) fabricated with 65 nm, 40 nm and 28 nm commercial bulk CMOS technologies is investigated. TID response is assessed employing Co-60 gamma ray source. The measurements indicate that the voltage reference is reduced by 5.67% in 28 nm, 0.56% in 40 nm and increased by 1.28% in 65 nm devices under irradiation up to 1.2 Mrad(Si) TID. After 48 hours of annealing, the voltage reference changes are just −1.84% in 28 nm, 0.14% in 40 nm and 1.14% in 65 nm. The obtained results demonstrate that the custom BGR has naturally superior TID response due to the circuit design margins.
Stability Improvement for One Cycle Controlled Boost Converters Based on Energy Balance Principle
WANG Lei, WU Qinghua, MA Wei, TANG Wenhu
2023, 32(6): 1293-1303. doi: 10.23919/cje.2021.00.204
Abstract(467) HTML (231) PDF(33)
Abstract:
Boost converters with one cycle control (OCC) are prone to exhibit oscillations as the Hopf bifurcation, which may degrade performances and limit the parameter stable region of converters. This work proposed a novel control strategy for suppressing such bifurcations and enlarging the parameter stability region of the boost system on the basis of the principle of energy balance in the circuit. Through analyzing of the stability and bifurcation condition, the results reflect that, the energy-based OCC can adjust the poles of the system transfer function, which ensures the stable operation of the system in an extended range of circuit parameters. Moreover, the orders of the transfer function will not be increased by such adjustments, thus the computational complexity of the transfer function will be increased. The theoretical analysis demonstrates the ability of the energy-based OCC for suppressing the bifurcations and enlarging the stable region of the system parameters. The results by simulation and experiment further prove the effectiveness of the proposed control strategy.
ARTIFICIAL INTELLIGENCE
Rating Text Classification with Weighted Negative Supervision on Classifier Layer
ZHANG Jun, QIU Longlong, SHEN Fanfan, HE Yueshun, TAN Hai, HE Yanxiang
2023, 32(6): 1304-1318. doi: 10.23919/cje.2021.00.339
Abstract(425) HTML (214) PDF(49)
Abstract:
Bidirectional encoder representations from transformers (BERT) gives full play to the advantages of the attention mechanism, improves the performance of sentence representation, and provides a better choice for various natural language understanding (NLU) tasks. Many methods using BERT as the pre-trained model achieve state-of-the-art performance in almost various text classification scenarios. Among them, the multi-task learning framework combining the negative supervision and the pre-trained model solves the issue of the model performance degradation that occurs as the semantic similarity of texts conflicts with the classification standards. The current model does not consider the degree of difference between labels, which leads to insufficient difference information learned by the model, and affects classification performance, especially in the rating classification tasks. On the basis of the multi-task learning model, this paper fully considers the degree of difference between labels, which is expressed by using weights to solve the above problems. We supervise negative samples on the classifier layer instead of the encoder layer, so that the classifier layer can also learn the difference information between the labels. Experimental results show that our model can not only performs well in 2-class and multi-class rating text classification tasks, but also performs well in different languages.
A Hybrid Music Recommendation Model Based on Personalized Measurement and Game Theory
WU Yun, LIN Jian, MA Yanlong
2023, 32(6): 1319-1328. doi: 10.23919/cje.2021.00.172
Abstract(934) HTML (472) PDF(45)
Abstract:
Music recommendation algorithms, from the perspective of real-time, can be classified into two categories: offline recommendation algorithms and online recommendation algorithms. To improve music recommendation accuracy, especially for the new music (users have no historic listening records on it), and real-time recommendation ability, and solve the interest drift problem simultaneously, we propose a hybrid music recommendation model based on personalized measurement and game theory. This model can be separated into two parts: an offline recommendation part (OFFLRP) and an online recommendation part (ONLRP). In the offline part, we emphasize users personalization. We introduce two metrics named user pursue-novelty degree (UPND) and music popularity (MP) to improve the traditional items-based collaborative filtering algorithm. In the online part, we try to solve the interest drift problem, which is a thorny problem in the offline part. We propose a novel online recommendation algorithm based on game theory. Experiments verify that the hybrid music recommendation model has higher new music recommendation accuracy, decent dynamical personalized recommendation ability, and real-time recommendation capability, and can substantially mitigate the problem of interest drift.
Fine-Grained Cross-Modal Fusion Based Refinement for Text-to-Image Synthesis
SUN Haoran, WANG Yang, LIU Haipeng, QIAN Biao
2023, 32(6): 1329-1340. doi: 10.23919/cje.2022.00.227
Abstract(362) HTML (181) PDF(41)
Abstract:
Text-to-image synthesis refers to generating visual-realistic and semantically consistent images from given textual descriptions. Previous approaches generate an initial low-resolution image and then refine it to be high-resolution. Despite the remarkable progress, these methods are limited in fully utilizing the given texts and could generate text-mismatched images, especially when the text description is complex. We propose a novel fine-grained text-image fusion based generative adversarial networks (FF-GAN), which consists of two modules: Fine-grained text-image fusion block (FF-Block) and global semantic refinement (GSR). The proposed FF-Block integrates an attention block and several convolution layers to effectively fuse the fine-grained word-context features into the corresponding visual features, in which the text information is fully used to refine the initial image with more details. And the GSR is proposed to improve the global semantic consistency between linguistic and visual features during the refinement process. Extensive experiments on CUB-200 and COCO datasets demonstrate the superiority of FF-GAN over other state-of-the-art approaches in generating images with semantic consistency to the given texts.
Reverse-Nearest-Neighbor-Based Clustering by Fast Search and Find of Density Peaks
ZHANG Chunhao, XIE Bin, ZHANG Yiran
2023, 32(6): 1341-1354. doi: 10.23919/cje.2022.00.165
Abstract(720) HTML (362) PDF(56)
Abstract:
Clustering by fast search and find of density peaks (CFSFDP) has the advantages of a novel idea, easy implementation, and efficient clustering. It has been widely recognized in various fields since it was proposed in Science in 2014. The CFSFDP algorithm also has certain limitations, such as non-unified sample density metrics defined by cutoff distance, the domino effect for the assignment of remaining samples triggered by unstable assignment strategy, and the phenomenon of picking wrong density peaks as cluster centers. We propose reverse-nearest-neighbor-based clustering by fast search and find of density peaks (RNN-CFSFDP) to avoid these shortcomings. We redesign and unify the sample density metric by introducing reverse nearest neighbor. The newly defined local density metric and the K-nearest neighbors of each sample are combined to make the assignment process more robust and alleviate the domino effect. A cluster fusion algorithm is proposed, which further alleviates the domino effect and effectively avoids the phenomenon of picking wrong density peaks as cluster centers. Experimental results on publicly available synthetic data sets and real-world data sets show that in most cases, the proposed algorithm is superior to or at least equivalent to the comparative methods in clustering performance. The proposed algorithm works better on manifold data sets and uneven density data sets.
INFORMATION SECURITY AND CRYPTOLOGY
A Time-Area-Efficient and Compact ECSM Processor over GF(p)
HE Shiyang, LI Hui, LI Qingwen, LI Fenghua
2023, 32(6): 1355-1366. doi: 10.23919/cje.2022.00.267
Abstract(451) HTML (228) PDF(33)
Abstract:
The elliptic curve scalar multiplication (ECSM) is the core of elliptic curve cryptography (ECC), which directly determines the performance of ECC. In this paper, a novel time-area-efficient and compact design of a 256-bit ECSM processor over GF( p ) for the resource-constrained device is proposed, where p can be selected flexibly according to the application scenario. A compact and efficient 256-bit modular adder/subtractor and an improved 256-bit Montgomery multiplier are designed. We select Jacobian coordinates for point doubling and mixed Jacobian-affine coordinates for point addition. We have improved the binary expansion algorithm to reduce 75% of the point addition operations. The clock consumption of each module in this architecture is constant, which can effectively resist side-channel attacks. Reuse technology is adopted in this paper to make the overall architecture more compact and efficient. The design architecture is implemented on Xilinx Kintex-7 (XC7K325T-2FFG900I), consuming 1439 slices, 2 DSPs, and 2 BRAMs. It takes about 7.9 ms at the frequency of 222.2 MHz and 1763k clock cycles to complete once 256-bit ECSM operation over GF( p ).