Improving the Accuracy-Latency Trade-off of Edge-Cloud Computation Offloading for Deep Learning Services
| Autor: | Nathaniel Hudson, Minoo Hosseinzadeh, Hana Khamfroush, Xiaobo Zhao, Daniel E. Lucani |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Flexibility (engineering)
Computer science business.industry Process (engineering) Deep learning Real-time computing Cloud computing 02 engineering and technology 010501 environmental sciences 01 natural sciences Reduction (complexity) 0202 electrical engineering electronic engineering information engineering Computation offloading 020201 artificial intelligence & image processing Enhanced Data Rates for GSM Evolution Artificial intelligence Latency (engineering) business 0105 earth and related environmental sciences |
| Zdroj: | Zhao, X, Hosseinzadeh, M, Hudson, N, Khamfroush, H & Lucani, D E 2020, Improving the Accuracy-Latency Trade-off of Edge-Cloud Computation Offloading for Deep Learning Services . in 2020 IEEE Globecom Workshops, GC Wkshps 2020-Proceedings ., 367470, IEEE, 2020 IEEE Globecom Workshops, GC Wkshps 2020-Proceedings, 2020 IEEE Globecom Workshops, GC Wkshps 2020, Virtual, Taipei, Taiwan, 07/12/2020 . https://doi.org/10.1109/GCWkshps50303.2020.9367470 GLOBECOM (Workshops) Zhao, X, Hosseinzadeh, M, Hudson, N, Khamfroush, H & Lucani Rötter, D E 2020, Improving the Accuracy-Latency Trade-off of Edge-Cloud Computation Offloading for Deep Learning Services . in 2020 IEEE Globecom Workshops, GC Wkshps 2020-Proceedings ., 367470, IEEE, 2020 IEEE Globecom Workshops, GC Wkshps 2020-Proceedings, 2020 IEEE Globecom Workshops, GC Wkshps 2020, Virtual, Taipei, Taiwan, 07/12/2020 . https://doi.org/10.1109/GCWkshps50303.2020.9367470, https://doi.org/10.1109/GCWkshps50303.2020.9367470 |
| DOI: | 10.1109/GCWkshps50303.2020.9367470 |
| Popis: | Offloading tasks to the edge or the Cloud has the potential to improve accuracy of classification and detection tasks as more powerful hardware and machine learning models can be used. The downside is the added delay introduced for sending the data to the Edge/Cloud. In delay-sensitive applications, it is usually necessary to strike a balance between accuracy and latency. However, the state of the art typically considers offloading all-or-nothing decisions, e.g., process locally or send all available data to the Edge (Cloud). Our goal is to expand the options in the accuracy-latency trade-off by allowing the source to send a fraction of the total data for processing. We evaluate the performance of image classifiers when faced with images that have been purposely reduced in quality in order to reduce traffic costs. Using three common models (SqueezeNet, GoogleNet, ResNet) and two data sets (Caltech101, ImageNet) we show that the Gompertz function provides a good approximation to determine the accuracy of a model given the fraction of the data of the image that is actually conveyed to the model. We formulate the offloading decision process using this new flexibility and show that a better overall accuracy-latency tradeoff is attained: 58% traffic reduction, 25% latency reduction, as well as 12% accuracy improvement. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|