Internet of Things (IoT) devices are rapidly expanding in many areas, including deep mines, space, industrial environments, and health monitoring systems. Most of the sensors and actuators are battery-powered, and these batteries have a finite lifespan. Maintaining and replacing these many batteries increases the maintenance cost of IoT systems and causes massive environmental damage. Energy-harvesting devices (EHDs) are the alternative and promising solution for these battery-operated IoT devices. These EHDs collect energy from the environment and use it for daily computations, like collecting and processing data from the sensors and actuators. Using EHDs in IoT reduces overall maintenance costs and makes the IoT system energy-sufficient. However, energy availability from these EHDs is unpredictable, resulting in frequent power failures. Most of these devices use volatile memories as storage elements, implying that all collected data and decisions made by the IoT devices are lost during frequent power failures, resulting in two possible overheads. First, the IoT device must execute the application from the beginning whenever power comes back. Second, IoT devices may make wrong decisions by considering incomplete data, i.e., data-inconsistency issues. To address these two challenges, a computing model is required that backs up the collected data during power failures and restores it for later computations; this type of computing is defined as intermittent computing. However, this computing model doesn't work with conventional processors or memories. Non-volatile memory and processors are required to design a battery-less IoT device that supports intermittent computing.

翻译：物联网（IoT）设备正快速扩展至诸多领域，包括深矿井、太空、工业环境和健康监测系统。大多数传感器和执行器依赖电池供电，而电池使用寿命有限。维护和更换大量电池会增加物联网系统的维护成本，并造成严重的环境损害。能量采集器件（EHDs）是这些电池供电式物联网设备的替代性和有前景的解决方案。这些EHDs从环境中收集能量，并将其用于日常计算，例如从传感器和执行器收集和处理数据。在物联网中使用EHDs可降低总体维护成本，并使得物联网系统实现能量自给。然而，这些EHDs提供的能量具有不可预测性，导致频繁的电源中断。大多数此类设备使用易失性存储器作为存储元件，这意味着在频繁的电源中断期间，物联网设备收集的所有数据及其所做决策都会丢失，从而引发两类可能的开销。首先，每当电源恢复时，物联网设备必须从头开始执行应用程序。其次，物联网设备可能因考虑不完整的数据而做出错误决策，即数据不一致问题。为应对这两项挑战，需要一种计算模型，该模型能在电源中断期间备份收集的数据，并在后续计算中恢复这些数据；这种计算类型定义为间歇性计算。然而，该计算模型不适用于传统处理器或存储器。为设计支持间歇性计算的无电池物联网设备，需要采用非易失性存储器和处理器。