| Autor: |
Bo-Jun Qiu, Cheng-Ying Hsieh, Jyh-Cheng Chen, Falko Dressler |
| Jazyk: |
angličtina |
| Rok vydání: |
2023 |
| Předmět: |
|
| Zdroj: |
IEEE Access, Vol 11, Pp 84985-85001 (2023) |
| Druh dokumentu: |
article |
| ISSN: |
2169-3536 |
| DOI: |
10.1109/ACCESS.2023.3303400 |
| Popis: |
Next-generation intelligent transportation systems aim to achieve many cooperative perception and cooperative driving functions that require considerable computational resources. Offloading such tasks via mobile edge computing is considered part of the solution; this approach is currently being studied within the scope of 5G networks and beyond. In the automotive context, such edge systems could be roadside units (RSUs), which can easily be overloaded at peak times. Vehicular microcloud approaches have been proposed to overcome such problems by sharing the computational resources of nearby cars. In this study, we propose an offloading system architecture to enable such offloading in a vehicular microcloud interconnected by a 5G core network. We model the system as a queueing model to derive closed-form solutions for selected performance metrics. Based on our insights, we propose the triple-check offloading algorithm (TCOA) to obtain both the best offloading ratio of the vehicular microcloud to the entire offloading system and the optimal maximum number of the remaining vehicle instances in the vehicular microcloud. Our simulation results show that the proposed TCOA achieves better system performance than four other offloading schemes in terms of cost, response time, service rate, and cost response-time production service rate division (CRPSD). |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
