Presentation
Automated Generation of SSD Stress Tests Using Offline Reinforcement Learning
DescriptionReinforcement learning has demonstrated optimization performance in various simulation environments, yet there has been limited evidence of its effectiveness in real-world scenarios.
In this study, we applied offline reinforcement learning in an SSD simulator with real product-level complexity. Attempting to design test cases that impose high loads on the SSD, we confirmed a reduction of over 50% in test input quantity compared to random testing.
To overcome the high complexity, we transformed the extensive input range supported by the product into an optimal range, reflecting product characteristics. We effectively represented internal information using a Graph Neural Network.
We propose an automated test generation framework that applies the reuse of trajactiories generated during the agent training process for training.
In this study, we applied offline reinforcement learning in an SSD simulator with real product-level complexity. Attempting to design test cases that impose high loads on the SSD, we confirmed a reduction of over 50% in test input quantity compared to random testing.
To overcome the high complexity, we transformed the extensive input range supported by the product into an optimal range, reflecting product characteristics. We effectively represented internal information using a Graph Neural Network.
We propose an automated test generation framework that applies the reuse of trajactiories generated during the agent training process for training.
Presenter
Event Type
Embedded Systems and Software
TimeWednesday, June 262:24pm - 2:42pm PDT
Location2010, 2nd Floor
AI
Embedded Systems
Engineering Tracks