Abstract
Recent anticipated advancements in ad hoc Wireless Mesh Networks (WMN) have made them strong natural candidates for Smart Grid’s Neighborhood Area Network (NAN) and the ongoing work on Advanced Metering Infrastructure (AMI). Fault detection in these types of energy systems has recently shown lots of interest in the data science community, where anomalous behavior from energy platforms is identified. This paper develops a new framework based on privacy reinforcement learning to accurately identify anomalous patterns in a distributed and heterogeneous energy environment. The local outlier factor is first performed to derive the local simple anomalous patterns in each site of the distributed energy platform. A reinforcement privacy learning is then established using blockchain technology to merge the local anomalous patterns into global complex anomalous patterns. Besides, different optimization strategies are suggested to improve the whole outlier detection process. To demonstrate the applicability of the proposed framework, intensive experiments have been carried out on well-known CASAS (Center of Advanced Studies in Adaptive Systems) platform. Our results show that our proposed framework outperforms the baseline fault detection solutions.
Highlights
Automated energy management is an interesting area of research, for distributed environments, where security and efficiency are crucial factors in the smart grid
We suggest a dedicated platform for identifying and learning deep anomalous patterns using blockchain technologies in heterogeneous distributed environments, which is suitable for security scenarios in industrial Internet of Things (IoT) using artificial intelligence (AI) techniques, e.g., reinforcement learning in the designed model
The local simple anomalous patterns determination is performed using the local outlier factor, with the integration of DTW (Dynamic Time Warping) strategy to determine the similarity between time series data, having different time lengths
Summary
Automated energy management is an interesting area of research, for distributed environments, where security and efficiency are crucial factors in the smart grid. There may exist many available technologies for communication, the ad hoc Wireless Mesh Network (WMN) has been well studied as a potential communication technology that is very well suited for the known requirements of the Smart grid’s Neighborhood Area Networks (NAN) [1,2] This has been due to the extended coverage (achieve through multi hopping), high throughput, low latency, and Quality of Service (QoS) abilities. This paper covers the stateof-the-art blockchain learning frameworks and introduces a new paradigm focused on blockchain learning to automatically detect time series of anomalous patterns in a distributed and heterogeneous setting. 1. We design a new method to help us identifying the complex anomalous patterns in distributed and heterogeneous time series.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have