Well understanding the access behavior of hot data is significant for NAND flash memory due to its crucial impact on the efficiency of garbage collection (GC) and wear leveling (WL), which respectively dominate the performance and life span of SSD. Generally, both GC and WL rely greatly on the recognition accuracy of hot data identification (HDI). However, in this paper, the first time we propose a novel concept of hot data prediction (HDP), where the conventional HDI becomes unnecessary. First, we develop a hybrid optimized echo state network (HOESN), where sufficiently unbiased and continuously shrunk output weights are learnt by a sparse regression based on L2 and L1/2 regularization. Second, quantum-behaved particle swarm optimization (QPSO) is employed to compute reservoir parameters (i.e., global scaling factor, reservoir size, scaling coefficient and sparsity degree) for further improving prediction accuracy and reliability. Third, in the test on a chaotic benchmark (Rossler), the HOESN performs better than those of six recent state-of-the-art methods. Finally, simulation results about six typical metrics tested on five real disk workloads and on-chip experiment outcomes verified from an actual SSD prototype indicate that our HOESN-based HDP can reliably promote the access performance and endurance of NAND flash memories.

中文翻译：

---

自学热点数据预测：Echo State Network 与 NAND Flash 的相遇

深入了解热数据的访问行为对于 NAND 闪存来说意义重大，因为它对垃圾收集 (GC) 和磨损均衡 (WL) 的效率有着至关重要的影响，这两个因素分别主导着 SSD 的性能和寿命。一般来说，GC 和 WL 都非常依赖于热数据识别 (HDI) 的识别精度。然而，在本文中，我们首次提出了热数据预测 (HDP) 的新概念，其中传统的 HDI 变得不必要。首先，我们开发了一个混合优化回声状态网络 (HOESN)，其中通过基于 L2 和 L1/2 正则化的稀疏回归学习充分无偏且连续收缩的输出权重。其次，采用量子行为粒子群优化 (QPSO) 来计算储层参数（即全局比例因子、储层大小、缩放系数和稀疏度）以进一步提高预测精度和可靠性。第三，在混沌基准（Rossler）的测试中，HOESN 的性能优于最近六种最先进的方法。最后，在五个真实磁盘工作负载上测试的六个典型指标的模拟结果和从实际 SSD 原型验证的片上实验结果表明，我们基于 HOESN 的 HDP 可以可靠地提升 NAND 闪存的访问性能和耐用性。