APRA: Adaptive Page Replacement Algorithm for NAND Flash Memory Storages

Abstract

This paper presents a new page replacement algorithm called Adaptive Page Replacement Algorithm (APRA), aiming at reducing the number of read, write, and erase operations and thereby improving the performance of NAND flash memory based storage systems. APRA uses a learning rule to adaptively and continually revise its parameter in response to diverse workloads with different access patterns. Experiments through simulation studies showed that the proposed algorithm performs better than other page replacement algorithms like LRU, CFLRU, CFLRU/C, LRU-WSR, in terms of read and write hit counts, and number of erase operations.