We adopt a reinforcement learning-based method to cache replacement strategy, aiming to improve the miss rate of existing traditional cache replacement policies. The main idea of modeling is to regard the strategy as a MDP so that we can employ DRL to learn cache eviction patterns.

In this project, I design and implement an AES encryptor and decryptor for any key length (128-bit, 192-bit, and 256-bit). The whole design is in pipeline architecture, continuous processing of input data. The number of stages depends on the key length. I also complete a test system for simulation with VHDL testbench and python script.