An RL-based controller using PPO, LSTM load prediction, and residual feature extraction adapts multi-model inference pipeline configurations on edge devices, improving QoS, reducing cost, and shortening decision time in a Kubernetes testbed.
The characteristics of cloud computing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Adaptive Configuration Selection for Multi-Model Inference Pipelines in Edge Computing
An RL-based controller using PPO, LSTM load prediction, and residual feature extraction adapts multi-model inference pipeline configurations on edge devices, improving QoS, reducing cost, and shortening decision time in a Kubernetes testbed.