In recent years, CNC workshops have gradually begun to transform from industrialization to digitalization. There are various problems in the interconnection between equipment and systems of different manufacturers. To achieve smooth information transmission between CNC lathe automatic processing units, it is necessary to establish a complete, normative information model. This paper analyzes the structure information and operation principle of CNC lathe automatic processing unit, understands the advantages and disadvantages of different information model protocols, develops an information model of CNC lathe automatic processing unit that conforms to the OPC UA protocol, and realizes interconnection.
{"title":"Design and Implementation of CNC Lathe Automatic Processing Unit Information Model Based on OPC UA","authors":"Dongwei Wang, Lunxing Li, Liaomo Zheng, Beibei Li, Xingjun Liu, Xiaoting Song","doi":"10.1109/ICCC56324.2022.10065741","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065741","url":null,"abstract":"In recent years, CNC workshops have gradually begun to transform from industrialization to digitalization. There are various problems in the interconnection between equipment and systems of different manufacturers. To achieve smooth information transmission between CNC lathe automatic processing units, it is necessary to establish a complete, normative information model. This paper analyzes the structure information and operation principle of CNC lathe automatic processing unit, understands the advantages and disadvantages of different information model protocols, develops an information model of CNC lathe automatic processing unit that conforms to the OPC UA protocol, and realizes interconnection.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124425103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065794
Chang Liu, Yingxi Chen
To solve the problem of insufficient extraction of weight information in binary quantization, this paper proposes a new training module based on W-regularization and variable cosine momentum. W-regularization is achieved by adjusting the network weights so that the weight values are optimised to ±1 and the parameters at different positions are optimised according to different functions. In addition, variable cosine momentum is designed so that parameters farther away from ±1 approach zero at high speed, which can significantly increase the speed of convergence and further improve quantization accuracy. Specifically, it outperforms the highest accuracy of bnn-free by 0.83% and 2.15% on the CIFAR-10, CIFAR-100 datasets, it also improved on both SVHN and TinyImage.
{"title":"A Neural Network Binary Quantization Method Based on W-Regularization and Variable Cosine Momentum","authors":"Chang Liu, Yingxi Chen","doi":"10.1109/ICCC56324.2022.10065794","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065794","url":null,"abstract":"To solve the problem of insufficient extraction of weight information in binary quantization, this paper proposes a new training module based on W-regularization and variable cosine momentum. W-regularization is achieved by adjusting the network weights so that the weight values are optimised to ±1 and the parameters at different positions are optimised according to different functions. In addition, variable cosine momentum is designed so that parameters farther away from ±1 approach zero at high speed, which can significantly increase the speed of convergence and further improve quantization accuracy. Specifically, it outperforms the highest accuracy of bnn-free by 0.83% and 2.15% on the CIFAR-10, CIFAR-100 datasets, it also improved on both SVHN and TinyImage.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124438800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065817
Jiayan Wu, Bin Song, Songbai He, Chang Wu
Digital predistortion (DPD) is an effective way to optimize the linearization of power amplifiers (PAs). The sampling rate of the feedback loop generally requires five times the input signal bandwidth due to the spectrum expansion, which results in great challenges of analog-to-digital converters (ADCs). An improved method in low feedback sampling rate DPD architecture is proposed in this paper to reduce the computational complexity of the downsampling DPD. By interpolating the low sampling output signal, the proposed method greatly reduces the algorithm complexity in terms of time alignment. In addition, an improved model containing fractional exponential power functions are presented to obtain higher modeling accuracy. To validate the proposed methods, simulations and experiments are performed respectively. With the downsampling rate of 100, the convergence speed of the proposed alignment algorithm is 10 times that of the traditional one, and the adjacent channel power ratio (ACPR) is improved by 3dB after predistortion.
{"title":"A Modified Signal Reconstruction Method in Low Feedback Sampling Rate Digital Predistortion","authors":"Jiayan Wu, Bin Song, Songbai He, Chang Wu","doi":"10.1109/ICCC56324.2022.10065817","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065817","url":null,"abstract":"Digital predistortion (DPD) is an effective way to optimize the linearization of power amplifiers (PAs). The sampling rate of the feedback loop generally requires five times the input signal bandwidth due to the spectrum expansion, which results in great challenges of analog-to-digital converters (ADCs). An improved method in low feedback sampling rate DPD architecture is proposed in this paper to reduce the computational complexity of the downsampling DPD. By interpolating the low sampling output signal, the proposed method greatly reduces the algorithm complexity in terms of time alignment. In addition, an improved model containing fractional exponential power functions are presented to obtain higher modeling accuracy. To validate the proposed methods, simulations and experiments are performed respectively. With the downsampling rate of 100, the convergence speed of the proposed alignment algorithm is 10 times that of the traditional one, and the adjacent channel power ratio (ACPR) is improved by 3dB after predistortion.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117345487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065792
Chunyu Liu, R. He, R. Xu, Ruifeng Chen, Jie Lv, Wei Zhang, Shaopeng Wang, Weiming Li, Wenpu Sun, Lizhe Li
Developing smart stations has become an important trend for the future rail traffic system, and the realization requires using Internet of Things (IoT) technology to improve performance. Although it has been widely considered to develop an IoT wireless sensor network to monitor subway station environment, there is still a lack of realistic measurement for deployment of IoT in station. In this paper, performances of long range (LoRa) and Narrow Band Internet of Things (NB-IoT) in subway station scenario are investigated. The transmission performances of LoRa in subway concourse, platforms, and passage scenarios are measured and evaluated. The received signal strength indication (RSSI), packet loss rate, and transmission delay are discussed based on measurements. It is found that LoRa performs fairly well in subway concourse and platform scenarios, with RSSI of more than -70 dBm and packet loss rate of less than 1%. However, in subway passage scenario, RSSI is relatively low and packet loss rate can be high. These results are helpful for deploying LoRa system in subway stations.
{"title":"Measurement and Analysis of LoRa Transmission Performance in Subway Station","authors":"Chunyu Liu, R. He, R. Xu, Ruifeng Chen, Jie Lv, Wei Zhang, Shaopeng Wang, Weiming Li, Wenpu Sun, Lizhe Li","doi":"10.1109/ICCC56324.2022.10065792","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065792","url":null,"abstract":"Developing smart stations has become an important trend for the future rail traffic system, and the realization requires using Internet of Things (IoT) technology to improve performance. Although it has been widely considered to develop an IoT wireless sensor network to monitor subway station environment, there is still a lack of realistic measurement for deployment of IoT in station. In this paper, performances of long range (LoRa) and Narrow Band Internet of Things (NB-IoT) in subway station scenario are investigated. The transmission performances of LoRa in subway concourse, platforms, and passage scenarios are measured and evaluated. The received signal strength indication (RSSI), packet loss rate, and transmission delay are discussed based on measurements. It is found that LoRa performs fairly well in subway concourse and platform scenarios, with RSSI of more than -70 dBm and packet loss rate of less than 1%. However, in subway passage scenario, RSSI is relatively low and packet loss rate can be high. These results are helpful for deploying LoRa system in subway stations.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"260 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117348452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10066015
Jiyu Dong, Yi Sun, Rong Fu, Chunming Zhao, Ming Jiang
In the existing designs for uplink multi-user Multiinput Multi-output (MU-MIMO) systems, centralized schemes usually provide good performance where the precoder is com-puted by the base station (BS) and then fed back to each terminal. However, this brings huge amounts of feedback overhead and therefore is hard to implement. The 5G protocol supports the use of the uplink codebook to deploy a precoder, hence the feedback cost is significantly compressed by transmitting only the index. In this letter, we develop a novel distributed precoder design for the uplink time division duplex (TDD) MU-MIMO systems subject to the transmit power constraint in terms of each terminal or each antenna. Taking both the error rate performance and the feedback overhead into account, the proposed scheme allows each terminal to obtain its own precoder based on the alternating optimization. Under the distributed strategy, no precoder feedback is required for the system, while with acceptable performance loss. In addition to the analysis, simulation results are presented to validate the effectiveness of the proposed scheme.
{"title":"Distributed Precoder Design for Uplink TDD MU-MIMO Systems","authors":"Jiyu Dong, Yi Sun, Rong Fu, Chunming Zhao, Ming Jiang","doi":"10.1109/ICCC56324.2022.10066015","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10066015","url":null,"abstract":"In the existing designs for uplink multi-user Multiinput Multi-output (MU-MIMO) systems, centralized schemes usually provide good performance where the precoder is com-puted by the base station (BS) and then fed back to each terminal. However, this brings huge amounts of feedback overhead and therefore is hard to implement. The 5G protocol supports the use of the uplink codebook to deploy a precoder, hence the feedback cost is significantly compressed by transmitting only the index. In this letter, we develop a novel distributed precoder design for the uplink time division duplex (TDD) MU-MIMO systems subject to the transmit power constraint in terms of each terminal or each antenna. Taking both the error rate performance and the feedback overhead into account, the proposed scheme allows each terminal to obtain its own precoder based on the alternating optimization. Under the distributed strategy, no precoder feedback is required for the system, while with acceptable performance loss. In addition to the analysis, simulation results are presented to validate the effectiveness of the proposed scheme.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124947741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065736
Jianguo Yu, Zhiyao Wang
This paper reports the design and simulation of 275GHz to 296GHz power amplifier employing embedding linear lossless reciprocity (LLR) network to boost maximum available gain to maximum achievable gain in 65nm CMOS process. The LLR network is realized by an inductor between the gate and drain of the transistor. The final simulation results show that the gain is greater than lOdB from 275GHz to 296GHz, and reaches a 29.4dB peak at 275GHz. And at 275GHz, saturated output power is -ldBm, IdB compression point of output power is -3.5dBm.
{"title":"A 275GHz to 296GHz Power Amplifier Using Embedding Network in 65nm-CMOS with 29.4dB Peak Power Gain","authors":"Jianguo Yu, Zhiyao Wang","doi":"10.1109/ICCC56324.2022.10065736","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065736","url":null,"abstract":"This paper reports the design and simulation of 275GHz to 296GHz power amplifier employing embedding linear lossless reciprocity (LLR) network to boost maximum available gain to maximum achievable gain in 65nm CMOS process. The LLR network is realized by an inductor between the gate and drain of the transistor. The final simulation results show that the gain is greater than lOdB from 275GHz to 296GHz, and reaches a 29.4dB peak at 275GHz. And at 275GHz, saturated output power is -ldBm, IdB compression point of output power is -3.5dBm.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123442601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10066031
Xiaojun Xia, Wenkang Shi, Ying Gao
In order to solve the problem of automatic detection of whether workers wear helmets and masks in construction sites, workshops and other scenarios, an improved YOLOv5 algorithm is proposed to improve the accuracy of simultaneous detection of helmets and masks. First, the CIOU_Loss with better effect is adopted, which considers the information of the center point distance of the bounding box and the scale information of the aspect ratio of the bounding box; The probability value of the category is sorted according to the category classification probability obtained by the classifier, which makes the results obtained by NMS more reasonable and effective. The experimental results show that the average accuracy of the improved algorithm for detecting helmet and mask wearing at the same time is 12.7% higher than that of the original algorithm.
{"title":"Simultaneous Detection of Helmet and Mask Wearing Based on YOLO Improved Algorithm","authors":"Xiaojun Xia, Wenkang Shi, Ying Gao","doi":"10.1109/ICCC56324.2022.10066031","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10066031","url":null,"abstract":"In order to solve the problem of automatic detection of whether workers wear helmets and masks in construction sites, workshops and other scenarios, an improved YOLOv5 algorithm is proposed to improve the accuracy of simultaneous detection of helmets and masks. First, the CIOU_Loss with better effect is adopted, which considers the information of the center point distance of the bounding box and the scale information of the aspect ratio of the bounding box; The probability value of the category is sorted according to the category classification probability obtained by the classifier, which makes the results obtained by NMS more reasonable and effective. The experimental results show that the average accuracy of the improved algorithm for detecting helmet and mask wearing at the same time is 12.7% higher than that of the original algorithm.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123759285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Short-term load forecasting(STLF) is an essential module of energy management system, which is of great signifi-cance to the economic dispatch and operation stability in smart grid. There is a large collection of methods developed for STLF, but it is still challenging to provide high precision STLF under different weather conditions which are the main factors affecting power generation load, especially for distributed photovoltaic power generation load. A short-term load forecasting method via model selection based on random forest is proposed in this paper to realize reliable and accurate daily power generation load forecasting under different conditions. We first perform clustering analysis on the raw data through K-means. In particular, we consider both weighted meteorological factors and historical load to improve clustering performance. Secondly, we establish a model pool consisting of state-of-the-art machine learning(ML) models which is selected from four alternative ML models, and each model is the best model for each cluster. Then, we train a random forest based on each set of data and its optimal model label. In the prediction stage, random forest is utilized to directly select an appropriate model from model pool to obtain the final prediction load. The performance of the proposed method is validated on real generation load of practical scenarios. The result indicates the superiority and advantages of the model selection based STLF method compared with the single model methods, and the mean absolute error(MAE), root mean square error(RMSE) and mean absolute percentage error(MAPE) are reduced by 118.5054(KW), 10.43% and 2.08%, respectively.
{"title":"A Short-Term Load Forecasting Method via Model Selection Based on Random Forest","authors":"Ziyi Li, Jingyi Zhang, Wenpeng Jing, Zhaoming Lu, Wei Zheng, X. Wen","doi":"10.1109/ICCC56324.2022.10065825","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065825","url":null,"abstract":"Short-term load forecasting(STLF) is an essential module of energy management system, which is of great signifi-cance to the economic dispatch and operation stability in smart grid. There is a large collection of methods developed for STLF, but it is still challenging to provide high precision STLF under different weather conditions which are the main factors affecting power generation load, especially for distributed photovoltaic power generation load. A short-term load forecasting method via model selection based on random forest is proposed in this paper to realize reliable and accurate daily power generation load forecasting under different conditions. We first perform clustering analysis on the raw data through K-means. In particular, we consider both weighted meteorological factors and historical load to improve clustering performance. Secondly, we establish a model pool consisting of state-of-the-art machine learning(ML) models which is selected from four alternative ML models, and each model is the best model for each cluster. Then, we train a random forest based on each set of data and its optimal model label. In the prediction stage, random forest is utilized to directly select an appropriate model from model pool to obtain the final prediction load. The performance of the proposed method is validated on real generation load of practical scenarios. The result indicates the superiority and advantages of the model selection based STLF method compared with the single model methods, and the mean absolute error(MAE), root mean square error(RMSE) and mean absolute percentage error(MAPE) are reduced by 118.5054(KW), 10.43% and 2.08%, respectively.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"169 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123791698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065791
Diaoyin Tan, Yu Liu, Huaxin Xiao, Yang Peng, Maojun Zhang
Weakly supervised semantic segmentation(WSSS) is a challenging task, which only requires category information for segmentation prediction. Existing WSSS methods can be divided into two types: CNN-based and transformer-based, and the ways of generating pseudo labels are different. The former uses Class Activation Mapping(Cam)to generate pseudo labels, but there is a problem that the activated areas are concentrated in the most discriminative parts. The latter one choose to use attention map from the multi-head self-attention(MHSA) block, but there also exist the problems of significant background noise and incoherent object area. In order to solve the problems above, we propose ICTCAM to help transformer block obtain the ability of CNN, which include two modules named deeper stem(DStem) and convolutional feed-forward network(CFFN). The experiment results show that our modules have improved the performance of the network and achieve 69.9% mIoU, which is a new state-of-the-art performance on the PASCAL VOC 2012 dataset compared with similar networks.
{"title":"ICTCAM: Introducing Convolution to Transformer-Based Weakly Supervised Semantic Segmentation","authors":"Diaoyin Tan, Yu Liu, Huaxin Xiao, Yang Peng, Maojun Zhang","doi":"10.1109/ICCC56324.2022.10065791","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065791","url":null,"abstract":"Weakly supervised semantic segmentation(WSSS) is a challenging task, which only requires category information for segmentation prediction. Existing WSSS methods can be divided into two types: CNN-based and transformer-based, and the ways of generating pseudo labels are different. The former uses Class Activation Mapping(Cam)to generate pseudo labels, but there is a problem that the activated areas are concentrated in the most discriminative parts. The latter one choose to use attention map from the multi-head self-attention(MHSA) block, but there also exist the problems of significant background noise and incoherent object area. In order to solve the problems above, we propose ICTCAM to help transformer block obtain the ability of CNN, which include two modules named deeper stem(DStem) and convolutional feed-forward network(CFFN). The experiment results show that our modules have improved the performance of the network and achieve 69.9% mIoU, which is a new state-of-the-art performance on the PASCAL VOC 2012 dataset compared with similar networks.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126945104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065712
Yunfei Gao, Mingliu Liu, Ziwei Mei, Yulin Hu
Recently, unmanned aerial vehicle (UAV)-assisted communication system has been introduced as a promising paradigm for the future space-aerial-terrestrial integrated communications. In this paper, we investigate an UAV communication system, where the UAV is employed to assist multiple ground loT devices for data collection in the area of interest with the existence of no-fly zones. Unlike existing approaches focusing only on simplified line-of-sigh (LoS)-dominant channel model, this paper considers a more practical probability LoS channel model, which considers path loss and shadowing. On the premise of satisfying the data throughput requirements of all ground loT devices, we intend to minimize the total task completion time by jointly optimizing UAV's trajectory and communication scheduling. To tackle the non-convex and difficult intractable problem, we first transform the original problem into an Markov decision process (MDP) problem, and then we propose a trajectory design solution based on deep reinforcement learning (DRL) algorithm for completion time minimization. The UAV serves as an agent in the process of execution algorithm, interacting with the environment and constantly improving its own mobile strategy. Finally, numerical results demonstrate that the proposed design contributes to significant performance enhancement and can be applied to practical scenarios with no-fly zones.
{"title":"Deep Reinforcement Learning Based UAV Trajectory Design for Data Collection Scenario with No-Fly Zones","authors":"Yunfei Gao, Mingliu Liu, Ziwei Mei, Yulin Hu","doi":"10.1109/ICCC56324.2022.10065712","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065712","url":null,"abstract":"Recently, unmanned aerial vehicle (UAV)-assisted communication system has been introduced as a promising paradigm for the future space-aerial-terrestrial integrated communications. In this paper, we investigate an UAV communication system, where the UAV is employed to assist multiple ground loT devices for data collection in the area of interest with the existence of no-fly zones. Unlike existing approaches focusing only on simplified line-of-sigh (LoS)-dominant channel model, this paper considers a more practical probability LoS channel model, which considers path loss and shadowing. On the premise of satisfying the data throughput requirements of all ground loT devices, we intend to minimize the total task completion time by jointly optimizing UAV's trajectory and communication scheduling. To tackle the non-convex and difficult intractable problem, we first transform the original problem into an Markov decision process (MDP) problem, and then we propose a trajectory design solution based on deep reinforcement learning (DRL) algorithm for completion time minimization. The UAV serves as an agent in the process of execution algorithm, interacting with the environment and constantly improving its own mobile strategy. Finally, numerical results demonstrate that the proposed design contributes to significant performance enhancement and can be applied to practical scenarios with no-fly zones.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122356650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：