The use of Dynamic Random Access Memory (DRAM) for storing Machine Learning (ML) models plays a critical role in accelerating ML inference tasks in the next generation of communication systems. However, periodic refreshment of DRAM results in wasteful energy consumption during standby periods, which is significant for resource-constrained Internet of Things (IoT) devices. To solve this problem, this work advocates two novel approaches: 1) wireless memory activation and 2) wireless memory approximation. These enable the wireless devices to efficiently manage the available memory by considering the timing aspects and relevance of ML model usage; hence, reducing the overall energy consumption. Numerical results show that our proposed scheme can realize smaller energy consumption than the always-on approach while satisfying the retrieval accuracy constraint.

翻译：在下一代通信系统中，使用动态随机存取存储器（DRAM）存储机器学习（ML）模型对于加速ML推理任务具有关键作用。然而，DRAM的周期性刷新在待机期间会导致显著的能源浪费，这对资源受限的物联网（IoT）设备尤为重要。为解决这一问题，本研究提出两种创新方法：1）无线内存激活与2）无线内存近似。这些方法使无线设备能够通过考虑ML模型使用的时间特性和相关性来高效管理可用内存，从而降低整体能耗。数值结果表明，在满足检索精度约束的条件下，所提方案能实现比持续运行方案更低的能耗。