Characterizing Perception Deep Learning Algorithms and Applications for Vehicular Edge Computing
Vehicular edge computing relies on the computational capabilities of interconnected edge devices to manage incoming requests from vehicles. This offloading process enhances the speed and efficiency of data handling, ultimately boosting the safety, performance, and reliability of connected vehicles....
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/18/1/31 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589378117959680 |
|---|---|
| author | Wang Feng Sihai Tang Shengze Wang Ying He Donger Chen Qing Yang Song Fu |
| author_facet | Wang Feng Sihai Tang Shengze Wang Ying He Donger Chen Qing Yang Song Fu |
| author_sort | Wang Feng |
| collection | DOAJ |
| description | Vehicular edge computing relies on the computational capabilities of interconnected edge devices to manage incoming requests from vehicles. This offloading process enhances the speed and efficiency of data handling, ultimately boosting the safety, performance, and reliability of connected vehicles. While previous studies have concentrated on processor characteristics, they often overlook the significance of the connecting components. Limited memory and storage resources on edge devices pose challenges, particularly in the context of deep learning, where these limitations can significantly affect performance. The impact of memory contention has not been thoroughly explored, especially regarding perception-based tasks. In our analysis, we identified three distinct behaviors of memory contention, each interacting differently with other resources. Additionally, our investigation of Deep Neural Network (DNN) layers revealed that certain convolutional layers experienced computation time increases exceeding <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2849</mn><mo>%</mo></mrow></semantics></math></inline-formula>, while activation layers showed a rise of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1173.34</mn><mo>%</mo></mrow></semantics></math></inline-formula>. Through our characterization efforts, we can model workload behavior on edge devices according to their configuration and the demands of the tasks. This allows us to quantify the effects of memory contention. To our knowledge, this study is the first to <i>characterize the influence of memory on vehicular edge computational workloads, with a strong emphasis on memory dynamics and DNN layers</i>. |
| format | Article |
| id | doaj-art-132d316da7844bd888709937e771c7a1 |
| institution | Kabale University |
| issn | 1999-4893 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj-art-132d316da7844bd888709937e771c7a12025-01-24T13:17:32ZengMDPI AGAlgorithms1999-48932025-01-011813110.3390/a18010031Characterizing Perception Deep Learning Algorithms and Applications for Vehicular Edge ComputingWang Feng0Sihai Tang1Shengze Wang2Ying He3Donger Chen4Qing Yang5Song Fu6Department of Computer Science and Engineering, University of North Texas, Denton, TX 76203, USADepartment of Computer Science, Schreiner University, Kerrville, TX 78028, USADepartment of Computer Science and Engineering, University of California, Santa Cruz, CA 95064, USADepartment of Computer Science and Engineering, University of North Texas, Denton, TX 76203, USADepartment of Computer Science and Engineering, University of North Texas, Denton, TX 76203, USADepartment of Computer Science and Engineering, University of North Texas, Denton, TX 76203, USADepartment of Computer Science and Engineering, University of North Texas, Denton, TX 76203, USAVehicular edge computing relies on the computational capabilities of interconnected edge devices to manage incoming requests from vehicles. This offloading process enhances the speed and efficiency of data handling, ultimately boosting the safety, performance, and reliability of connected vehicles. While previous studies have concentrated on processor characteristics, they often overlook the significance of the connecting components. Limited memory and storage resources on edge devices pose challenges, particularly in the context of deep learning, where these limitations can significantly affect performance. The impact of memory contention has not been thoroughly explored, especially regarding perception-based tasks. In our analysis, we identified three distinct behaviors of memory contention, each interacting differently with other resources. Additionally, our investigation of Deep Neural Network (DNN) layers revealed that certain convolutional layers experienced computation time increases exceeding <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2849</mn><mo>%</mo></mrow></semantics></math></inline-formula>, while activation layers showed a rise of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1173.34</mn><mo>%</mo></mrow></semantics></math></inline-formula>. Through our characterization efforts, we can model workload behavior on edge devices according to their configuration and the demands of the tasks. This allows us to quantify the effects of memory contention. To our knowledge, this study is the first to <i>characterize the influence of memory on vehicular edge computational workloads, with a strong emphasis on memory dynamics and DNN layers</i>.https://www.mdpi.com/1999-4893/18/1/31vehicular edge computingdeep learningautonomous vehiclesperception algorithms |
| spellingShingle | Wang Feng Sihai Tang Shengze Wang Ying He Donger Chen Qing Yang Song Fu Characterizing Perception Deep Learning Algorithms and Applications for Vehicular Edge Computing Algorithms vehicular edge computing deep learning autonomous vehicles perception algorithms |
| title | Characterizing Perception Deep Learning Algorithms and Applications for Vehicular Edge Computing |
| title_full | Characterizing Perception Deep Learning Algorithms and Applications for Vehicular Edge Computing |
| title_fullStr | Characterizing Perception Deep Learning Algorithms and Applications for Vehicular Edge Computing |
| title_full_unstemmed | Characterizing Perception Deep Learning Algorithms and Applications for Vehicular Edge Computing |
| title_short | Characterizing Perception Deep Learning Algorithms and Applications for Vehicular Edge Computing |
| title_sort | characterizing perception deep learning algorithms and applications for vehicular edge computing |
| topic | vehicular edge computing deep learning autonomous vehicles perception algorithms |
| url | https://www.mdpi.com/1999-4893/18/1/31 |
| work_keys_str_mv | AT wangfeng characterizingperceptiondeeplearningalgorithmsandapplicationsforvehicularedgecomputing AT sihaitang characterizingperceptiondeeplearningalgorithmsandapplicationsforvehicularedgecomputing AT shengzewang characterizingperceptiondeeplearningalgorithmsandapplicationsforvehicularedgecomputing AT yinghe characterizingperceptiondeeplearningalgorithmsandapplicationsforvehicularedgecomputing AT dongerchen characterizingperceptiondeeplearningalgorithmsandapplicationsforvehicularedgecomputing AT qingyang characterizingperceptiondeeplearningalgorithmsandapplicationsforvehicularedgecomputing AT songfu characterizingperceptiondeeplearningalgorithmsandapplicationsforvehicularedgecomputing |