Intelligent Prediction of Flash Lifetime via Online Domain Adaptation

Abstract

To resolve the low generalization ability of the flash lifetime model caused by a small training sample, we propose a multiple source ensemble online domain adaptation scheme, called MSE. MSE uses multiple offline source blocks to assist in establishing a lifetime prediction model for the online target block. MSE migrates information from these blocks to the target block, effectively solving the pain point of insufficient samples for the target block. We simulate the actual use scenarios of NAND flash on the FPGA-based test platform. Experimental results show that prediction accuracy of MSE exceeds 0.91 using only a small number of samples of the target block. Therefore, MSE can be used to improve the space utilization of the flash with low overhead.