Neural Network (NN)-based Solutions for automatic tuning leverage the power of artificial neural networks to model the complex relationships between configuration parameters and system performance, enabling efficient tuning.
Tan et al. propose iBTune, an individualized buffer tuning method utilizing information from similar workloads to optimize buffer pool sizes, maintaining quality of service for response times.
The design of a pairwise deep neural network predicts upper bounds on response times, ensuring service level agreements are met through learned performance metrics.
By optimizing the configuration of resources dynamically, NN-based solutions minimize manual intervention and exhaustive searching in tuning parameters, leading to improved efficiency in performance.
#neural-networks #automatic-tuning #buffer-management #system-performance #configuration-optimization
Collection
[
|
...
]