Pub Date : 2023-06-14DOI: 10.1109/BMSB58369.2023.10211326
Xiang-Yu Chen, Ping Han, Yanqing Huang, Yi Han, Yi Zhong, Zhuo Li, Zhenhui Yuan, Gabriel-Miro Muntean
Image enhancement increases the perceived quality and improves the experience of viewers by processing images that are difficult to see, such as due to low light or overexposure. This is specifically important for night monitoring cameras or for the performance of visual-based night autonomous driving algorithms. This paper proposes a multi-adaptive fusion image enhancement algorithm (MAAF) to adaptively select and fuse Histogram Equalization (HE), Multi-scale Retinex (MSR), and Gamma Correction (GC) in the image frequency domain through Discrete Cosine Transform (DCT). Based on a genetic algorithm, the proposed MAAF combines the advantages of the different methods in terms of lighting enhancement (HE), edge enhancement (MSR), and overexposed image enhancement (GC) to achieve an overall performance optimization. A comprehensive evaluation score (CES) is also proposed in this paper as an overall assessment metric. MAAF was evaluated in terms of multiple metrics, including entropy, average gradient, contrast, and PSNR. Experimental results showed that MAAF obtains the highest CES compared with other algorithms.
{"title":"A Genetic Algorithm-based Image Enhancement Approach for Autonomous Driving at Night","authors":"Xiang-Yu Chen, Ping Han, Yanqing Huang, Yi Han, Yi Zhong, Zhuo Li, Zhenhui Yuan, Gabriel-Miro Muntean","doi":"10.1109/BMSB58369.2023.10211326","DOIUrl":"https://doi.org/10.1109/BMSB58369.2023.10211326","url":null,"abstract":"Image enhancement increases the perceived quality and improves the experience of viewers by processing images that are difficult to see, such as due to low light or overexposure. This is specifically important for night monitoring cameras or for the performance of visual-based night autonomous driving algorithms. This paper proposes a multi-adaptive fusion image enhancement algorithm (MAAF) to adaptively select and fuse Histogram Equalization (HE), Multi-scale Retinex (MSR), and Gamma Correction (GC) in the image frequency domain through Discrete Cosine Transform (DCT). Based on a genetic algorithm, the proposed MAAF combines the advantages of the different methods in terms of lighting enhancement (HE), edge enhancement (MSR), and overexposed image enhancement (GC) to achieve an overall performance optimization. A comprehensive evaluation score (CES) is also proposed in this paper as an overall assessment metric. MAAF was evaluated in terms of multiple metrics, including entropy, average gradient, contrast, and PSNR. Experimental results showed that MAAF obtains the highest CES compared with other algorithms.","PeriodicalId":13080,"journal":{"name":"IEEE international Symposium on Broadband Multimedia Systems and Broadcasting","volume":"1 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87158057","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 : 2023-06-14DOI: 10.1109/BMSB58369.2023.10211157
Jing Tang, Fujia Liu, Xiaoting Ma, Bo Lei, Yunpeng Xie
With the trend of more intelligence, richer service forms and more resources consumed, the underlying network architecture of multimedia services needs to be innovated urgently. This paper discusses a new network infrastructure architecture for multimedia services based on cloud-network convergence. The deep integration of computing and network is practiced by multimedia rendering service to build the computing power network (CPN) under this architecture. This architecture can adapt to the increasing complexity and uncertainty of new multimedia services in the future.
{"title":"A new network infrastructure architecture arising from the multimedia service evolution","authors":"Jing Tang, Fujia Liu, Xiaoting Ma, Bo Lei, Yunpeng Xie","doi":"10.1109/BMSB58369.2023.10211157","DOIUrl":"https://doi.org/10.1109/BMSB58369.2023.10211157","url":null,"abstract":"With the trend of more intelligence, richer service forms and more resources consumed, the underlying network architecture of multimedia services needs to be innovated urgently. This paper discusses a new network infrastructure architecture for multimedia services based on cloud-network convergence. The deep integration of computing and network is practiced by multimedia rendering service to build the computing power network (CPN) under this architecture. This architecture can adapt to the increasing complexity and uncertainty of new multimedia services in the future.","PeriodicalId":13080,"journal":{"name":"IEEE international Symposium on Broadband Multimedia Systems and Broadcasting","volume":"96 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88440820","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 : 2023-06-14DOI: 10.1109/BMSB58369.2023.10211534
Chenshi Ding, Can Yang, Jian Xiong, Peng Cheng
With the availability of Unmanned Air Vehicles (UAVs), low-cost and multi-view drone live broadcasting can present a better live effect for outdoor events. However, small UAVs usually cannot meet the requirements of uninterrupted long-distance live broadcast tasks due to the limitation of its load capacity. In this paper, we focus on the strategy of UAV aerial replenishment with the collaborative air-ground system in order to solve the endurance problem in the marathon drone live broadcast scenario. We adopt reinforcement learning algorithm to optimize the replenishment strategy of the collaborative air-ground system based on the fixed flight path of the Task UAV. Simulation results validate that the reinforcement learning algorithm can greatly reduce the replenishment consumption and ensure the best working status of the Task UAV.
{"title":"On Collaborative Air-Ground Replenishment of Combined UAVs for Live Broadcast","authors":"Chenshi Ding, Can Yang, Jian Xiong, Peng Cheng","doi":"10.1109/BMSB58369.2023.10211534","DOIUrl":"https://doi.org/10.1109/BMSB58369.2023.10211534","url":null,"abstract":"With the availability of Unmanned Air Vehicles (UAVs), low-cost and multi-view drone live broadcasting can present a better live effect for outdoor events. However, small UAVs usually cannot meet the requirements of uninterrupted long-distance live broadcast tasks due to the limitation of its load capacity. In this paper, we focus on the strategy of UAV aerial replenishment with the collaborative air-ground system in order to solve the endurance problem in the marathon drone live broadcast scenario. We adopt reinforcement learning algorithm to optimize the replenishment strategy of the collaborative air-ground system based on the fixed flight path of the Task UAV. Simulation results validate that the reinforcement learning algorithm can greatly reduce the replenishment consumption and ensure the best working status of the Task UAV.","PeriodicalId":13080,"journal":{"name":"IEEE international Symposium on Broadband Multimedia Systems and Broadcasting","volume":"26 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75705521","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}
In order to cope with the emergency scenarios, this paper proposed a heterogeneous low altitude platform deployment strategy to realize a seamless and continuous service wireless network. We designed an aerial network deployment Architecture composed of aerial base station (AeBS), aerial remote radio head (AeRRH) and millimeter-wave Unmanned Aerial Vehicle (mmW-UAV). The coverage problem of AeBS and AeRRH is solved through the circle packing algorithm and fixed coverage greedy deployment algorithm. The gradient enhanced greedy expectation maximization is used to implement the mmW-UAV to enhance local capacity. Finally, the numerical results show that the proposed strategy can effectively extend the network coverage.
{"title":"Heterogeneous Low Altitude Platforms Deployment Strategy for Emergency Network","authors":"Mengjun Yin, Wei-Jhih Lin, Shuai Wu, Xian Gao, Wenjing Li, Peng Yu, Lei Feng","doi":"10.1109/BMSB58369.2023.10211215","DOIUrl":"https://doi.org/10.1109/BMSB58369.2023.10211215","url":null,"abstract":"In order to cope with the emergency scenarios, this paper proposed a heterogeneous low altitude platform deployment strategy to realize a seamless and continuous service wireless network. We designed an aerial network deployment Architecture composed of aerial base station (AeBS), aerial remote radio head (AeRRH) and millimeter-wave Unmanned Aerial Vehicle (mmW-UAV). The coverage problem of AeBS and AeRRH is solved through the circle packing algorithm and fixed coverage greedy deployment algorithm. The gradient enhanced greedy expectation maximization is used to implement the mmW-UAV to enhance local capacity. Finally, the numerical results show that the proposed strategy can effectively extend the network coverage.","PeriodicalId":13080,"journal":{"name":"IEEE international Symposium on Broadband Multimedia Systems and Broadcasting","volume":"3 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75990774","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 : 2023-06-14DOI: 10.1109/BMSB58369.2023.10211213
Zehua Chen, Zhili Wang, Xingyu Chen
More and more attention has been attracted to online flow scheduling mechanisms in Time-Sensitive Networks (TSN) because of the significantly increasing demand for low delay and low jitter communication in fields such as smart factories or automatic vehicles. However, because of the lack of flow information known in advance, such as when and what kind of flows will arrive and will be scheduled, it’s easy for most online routing and scheduling methods to reach the bottleneck of flow scheduling in the scenario where there are time-triggered flows with large period differences to be scheduled, resulting in a low scheduling success rate.In this paper, a flow preprocessing method is proposed to filter flows with certain characteristics that have potential negative influence on the overall scheduling success rate or bandwidth utilization according to their periods and arrival probability. The proposed method can be easily superimposed on any kind of online routing and scheduling methods in TSN to improve performance. The flow preprocessing method is evaluated in scenarios with different numbers and types of flows, and the result shows that the flow scheduling with our preprocessing method outperform the flow scheduling without preprocessing in terms of scheduling success rate, bandwidth utilization and computation time.
{"title":"Flow Preprocessing for Online Routing and Scheduling in Time-Sensitive Networks","authors":"Zehua Chen, Zhili Wang, Xingyu Chen","doi":"10.1109/BMSB58369.2023.10211213","DOIUrl":"https://doi.org/10.1109/BMSB58369.2023.10211213","url":null,"abstract":"More and more attention has been attracted to online flow scheduling mechanisms in Time-Sensitive Networks (TSN) because of the significantly increasing demand for low delay and low jitter communication in fields such as smart factories or automatic vehicles. However, because of the lack of flow information known in advance, such as when and what kind of flows will arrive and will be scheduled, it’s easy for most online routing and scheduling methods to reach the bottleneck of flow scheduling in the scenario where there are time-triggered flows with large period differences to be scheduled, resulting in a low scheduling success rate.In this paper, a flow preprocessing method is proposed to filter flows with certain characteristics that have potential negative influence on the overall scheduling success rate or bandwidth utilization according to their periods and arrival probability. The proposed method can be easily superimposed on any kind of online routing and scheduling methods in TSN to improve performance. The flow preprocessing method is evaluated in scenarios with different numbers and types of flows, and the result shows that the flow scheduling with our preprocessing method outperform the flow scheduling without preprocessing in terms of scheduling success rate, bandwidth utilization and computation time.","PeriodicalId":13080,"journal":{"name":"IEEE international Symposium on Broadband Multimedia Systems and Broadcasting","volume":"10 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82069011","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 : 2023-06-14DOI: 10.1109/BMSB58369.2023.10211630
Jie Mei, Min Wei, Yukun Sun, Jiacong Li, Gefan Zhou, Xing Zhang
Computing Power Network (CPN) is a new network paradigm for next generation communication systems. Meanwhile, Federated Learning (FL) has attracted more and more attention nowadays. However, there are few researches on the resource scheduling problem of federated learning in computing power network. There are a large number of heterogeneous computing resources available in the computing power network, so efficient utilization of resources in CPN for federated learning is very important. Therefore, our research focuses on the resource scheduling problem of federated learning in computing power networks to make up for the shortcomings of current related research. In this paper, we propose a framework and functional architecture combining CPN and federated learning for the purpose of resource optimization in federated learning. Besides, we show that task offloading using split learning can significantly improve the computational performance of federated learning, especially on local computing.
{"title":"The Architecture of Computing Power Network Towards Federated Learning: Paradigms and Perspectives","authors":"Jie Mei, Min Wei, Yukun Sun, Jiacong Li, Gefan Zhou, Xing Zhang","doi":"10.1109/BMSB58369.2023.10211630","DOIUrl":"https://doi.org/10.1109/BMSB58369.2023.10211630","url":null,"abstract":"Computing Power Network (CPN) is a new network paradigm for next generation communication systems. Meanwhile, Federated Learning (FL) has attracted more and more attention nowadays. However, there are few researches on the resource scheduling problem of federated learning in computing power network. There are a large number of heterogeneous computing resources available in the computing power network, so efficient utilization of resources in CPN for federated learning is very important. Therefore, our research focuses on the resource scheduling problem of federated learning in computing power networks to make up for the shortcomings of current related research. In this paper, we propose a framework and functional architecture combining CPN and federated learning for the purpose of resource optimization in federated learning. Besides, we show that task offloading using split learning can significantly improve the computational performance of federated learning, especially on local computing.","PeriodicalId":13080,"journal":{"name":"IEEE international Symposium on Broadband Multimedia Systems and Broadcasting","volume":"73 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90410251","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 : 2023-06-14DOI: 10.1109/BMSB58369.2023.10211120
Yonghua Huo, Y. Liu, Wei Huang, Chengwen Fan, Yang Yang
With the rapid development of the IoT business, the IoT is showing a trend of large-scale and complex, and the types and quantities of terminal devices connected to the IoT system are constantly increasing, which puts forward higher requirements for the stability of the IoT. At present, the fault of IoT terminal device is unavoidable, and the existing research in the field of IoT terminals fault mainly focuses on the monitoring and diagnosis of faults. It is particularly important to make accurate and timely prediction before the fault occurs. In this paper, a IoT terminal fault prediction algorithm based on improved ResNet and BiLSTM and a Knowledge Review algorithm based on ECA module and Channel Connection loss are are proposed, which provides an effective solution for fault prediction of IoT terminal device.
{"title":"Fault Prediction of IoT Terminals based on Improved ResNet and BiLSTM Models","authors":"Yonghua Huo, Y. Liu, Wei Huang, Chengwen Fan, Yang Yang","doi":"10.1109/BMSB58369.2023.10211120","DOIUrl":"https://doi.org/10.1109/BMSB58369.2023.10211120","url":null,"abstract":"With the rapid development of the IoT business, the IoT is showing a trend of large-scale and complex, and the types and quantities of terminal devices connected to the IoT system are constantly increasing, which puts forward higher requirements for the stability of the IoT. At present, the fault of IoT terminal device is unavoidable, and the existing research in the field of IoT terminals fault mainly focuses on the monitoring and diagnosis of faults. It is particularly important to make accurate and timely prediction before the fault occurs. In this paper, a IoT terminal fault prediction algorithm based on improved ResNet and BiLSTM and a Knowledge Review algorithm based on ECA module and Channel Connection loss are are proposed, which provides an effective solution for fault prediction of IoT terminal device.","PeriodicalId":13080,"journal":{"name":"IEEE international Symposium on Broadband Multimedia Systems and Broadcasting","volume":"5 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86816522","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 : 2023-06-14DOI: 10.1109/BMSB58369.2023.10211449
Daifu Yan, Min Jia, Qingbei Guo, Xuemai Gu
Conventional communication systems are generally based on modular design, since the modules are optimized separately, the system can not achieve the optimal performance. An end-to-end communication system model can be implemented by deep learning, which can improve the transmission performance. However, the channel environment is changeable and unknown, which make the optimization of the end-to-end communication system impossible. Recently, the birth of the deep convolutional generative adversarial networks (DCGAN) can simulate unknown channels and solve the optimization problem of end-to-end systems. Then, the DCGAN has poor training stability, and the problems of over-fitting and gradient disappearance caused by it will lead to performance degradation. In this paper, we propose a residual-based DCGAN model to alleviate these problems. Specifically, we introduce a residual block structure, which effectively alleviates the over-fitting problem of the gradient. In addition, we introduce the Wasserstein distance to measure the difference between the generated data and the real data distribution, and further solve the problem of model training instability. Simulation results show that our proposed Residual DCGAN-based model effectively improves the block error rate (BLER) performance compared with traditional methods.
{"title":"Unknown Channel End-to-End Learning of Communication System With Residual DCGAN","authors":"Daifu Yan, Min Jia, Qingbei Guo, Xuemai Gu","doi":"10.1109/BMSB58369.2023.10211449","DOIUrl":"https://doi.org/10.1109/BMSB58369.2023.10211449","url":null,"abstract":"Conventional communication systems are generally based on modular design, since the modules are optimized separately, the system can not achieve the optimal performance. An end-to-end communication system model can be implemented by deep learning, which can improve the transmission performance. However, the channel environment is changeable and unknown, which make the optimization of the end-to-end communication system impossible. Recently, the birth of the deep convolutional generative adversarial networks (DCGAN) can simulate unknown channels and solve the optimization problem of end-to-end systems. Then, the DCGAN has poor training stability, and the problems of over-fitting and gradient disappearance caused by it will lead to performance degradation. In this paper, we propose a residual-based DCGAN model to alleviate these problems. Specifically, we introduce a residual block structure, which effectively alleviates the over-fitting problem of the gradient. In addition, we introduce the Wasserstein distance to measure the difference between the generated data and the real data distribution, and further solve the problem of model training instability. Simulation results show that our proposed Residual DCGAN-based model effectively improves the block error rate (BLER) performance compared with traditional methods.","PeriodicalId":13080,"journal":{"name":"IEEE international Symposium on Broadband Multimedia Systems and Broadcasting","volume":"16 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87808429","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}
SDN, NFV and other technologies increase the complexity of data network systems, resulting in an increase in the probability of network failures and the difficulty of maintenance. In order to design a more practical fault management framework and mechanism, the data network environment is analyzed first. Based on the characteristics of data network environment and network elements, a fault management architecture based on artificial intelligence is proposed. The architecture includes device layer, data acquisition layer, data analysis layer and data management layer. In order to improve the application value and convenience of the fault management architecture, the elastic strategy, self-healing strategy and work order distribution mechanism of the data management layer are designed in detail. In the performance analysis, from the implementation feasibility and performance aspects, it is verified that the fault management mechanism proposed in this paper has good application value.
{"title":"Research on Fault Management System based on Artificial Intelligence in Data Network","authors":"Yunzhou Dong, Xinyu Wang, Fangyou Fu, Zhengdong Lin, Chaona Yin, Yingkun Liao, Peng Lin","doi":"10.1109/BMSB58369.2023.10211345","DOIUrl":"https://doi.org/10.1109/BMSB58369.2023.10211345","url":null,"abstract":"SDN, NFV and other technologies increase the complexity of data network systems, resulting in an increase in the probability of network failures and the difficulty of maintenance. In order to design a more practical fault management framework and mechanism, the data network environment is analyzed first. Based on the characteristics of data network environment and network elements, a fault management architecture based on artificial intelligence is proposed. The architecture includes device layer, data acquisition layer, data analysis layer and data management layer. In order to improve the application value and convenience of the fault management architecture, the elastic strategy, self-healing strategy and work order distribution mechanism of the data management layer are designed in detail. In the performance analysis, from the implementation feasibility and performance aspects, it is verified that the fault management mechanism proposed in this paper has good application value.","PeriodicalId":13080,"journal":{"name":"IEEE international Symposium on Broadband Multimedia Systems and Broadcasting","volume":"6 5","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91493623","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 : 2023-06-14DOI: 10.1109/BMSB58369.2023.10211159
Xiaoyao Huang, Bo Lei, Min Wei, Guo Ji, Hang Lv
An appealing technology that merges computing and network resources to offer convergent services is the computing power network, which has attracted a lot of interest. In this paper, we study the task routing problem in the heterogeneous computing power network to minimize the loss of task value of the system. We first formulate the problem as a mixed integer nonlinear programming problem (MINP). To solve the problem, we propose a task Value aware Ant Colony algorithm(VACO) and deduced the complexity of the algorithm. The proposed algorithm VACO searches for optimal traversal in the directed graph by multiple ants for multiple rounds based on the designed task value aware pheromone concentration and transition probability function to achieve the minimum value loss routing scheme. Finally, the proposed algorithm’s excellent performance was demonstrated through comprehensive simulations conducted in the end.
{"title":"Task Value Aware Optimization of Routing for Computing Power Network","authors":"Xiaoyao Huang, Bo Lei, Min Wei, Guo Ji, Hang Lv","doi":"10.1109/BMSB58369.2023.10211159","DOIUrl":"https://doi.org/10.1109/BMSB58369.2023.10211159","url":null,"abstract":"An appealing technology that merges computing and network resources to offer convergent services is the computing power network, which has attracted a lot of interest. In this paper, we study the task routing problem in the heterogeneous computing power network to minimize the loss of task value of the system. We first formulate the problem as a mixed integer nonlinear programming problem (MINP). To solve the problem, we propose a task Value aware Ant Colony algorithm(VACO) and deduced the complexity of the algorithm. The proposed algorithm VACO searches for optimal traversal in the directed graph by multiple ants for multiple rounds based on the designed task value aware pheromone concentration and transition probability function to achieve the minimum value loss routing scheme. Finally, the proposed algorithm’s excellent performance was demonstrated through comprehensive simulations conducted in the end.","PeriodicalId":13080,"journal":{"name":"IEEE international Symposium on Broadband Multimedia Systems and Broadcasting","volume":"41 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91171437","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：