The big data generated by Industry 4.0 is expected to increase 20-fold in the next ten years and it has raised various challenges in Industrial Wireless Sensor Networks (IWSNs). Among these challenges, detecting different types of anomalies of industrial electricity consumption in an accurate and timely manner is a priority. If not handled properly, these anomalies could lead to serious consequences, such as irregular fire and paralyzed power system components. While existing anomaly detection techniques may be efficient for old systems, they are now faced with big transmitted data. Therefore, it is important to design new methods that can detect the electricity consumption anomaly and carry out appropriate actions. In this article, we first review several existing work on anomaly detection schemes, and then introduce the system and monitoring models. Then, we present a new framework that aims to detect electricity consumption anomalies accurately and timely using sensor processing, smart meter readings, machine learning and blockchain.

预计在未来十年中，工业4.0产生的大数据将增长20倍，并在工业无线传感器网络（IWSN）中提出了各种挑战。在这些挑战中，以准确及时的方式检测不同类型的工业用电异常是当务之急。如果处理不当，这些异常可能会导致严重后果，例如不规则的火灾和瘫痪的电源系统组件。尽管现有的异常检测技术对于旧系统可能是有效的，但它们现在面临着大量传输的数据。因此，重要的是设计新的方法来检测耗电量异常并采取适当的措施。在本文中，我们首先回顾一下有关异常检测方案的现有工作，然后介绍系统和监控模型。然后，我们提出了一个新框架，旨在使用传感器处理，智能电表读数，机器学习和区块链来准确及时地检测出用电量异常。