In the realm of advanced smart grids, real-time monitoring and control of substation equipment and transmission lines have become essential. This article focuses on cloud-based monitoring prediction and control of sub...
详细信息
In the realm of advanced smart grids, real-time monitoring and control of substation equipment and transmission lines have become essential. This article focuses on cloud-based monitoring prediction and control of substation transformer and transmission lines using Artificial Intelligence (AI) and Internet of Things (IoT). 3D printed model of a transformer, transmission towers and lines equipped with various sensors are designed and developed to acquire data from the transformer and transmission lines. The main objective of this paper is to acquire data from installed sensors and run dataanalytics on the cloud. And most importantly, predict Transformer Health Index (HI) and identify fault conditions in the transmission lines. cloud-based big dataanalytics are employed to train and test Machine Learning (ML) algorithms for HI prediction. Multiple regression ML algorithms are trained and tested on the cloud, with their results compared. The prototype is designed for 440 V, 10 A, 50 Hz, demonstrating the proposed cloud-based monitoring, control, and prediction approaches. The hardware setup is based on a Cortex ARM controller (ARDUINO MKR 1000) and incorporates a PT (Potential Transformer), CT (Current Transformer), PZEM 004T, MQ5, IR (Infrared), and ultrasonic sensors. Transformer data, such as temperature, oil level, and CH 4 levels, are sensed and logged onto the cloud, which is then used to train and test ML algorithms for transformer HI predictions. Additionally, 3-phase, 3-wire transmission lines are laid across three transmission towers, and line current data is also collected and logged onto the cloud for fault detection. HTTP (Hypertext Transfer Protocol) request is incorporated into a MATLAB analysis app on the cloud to send fault notification emails to technical personnel and resolve the fault by activating a relay. The results presented demonstrate the effectiveness of cloud monitoring, transformer health analytics, HI prediction, and the fault resolution
Unobtrusive gathering of personal or environmental data using a smartphone can provide the basis for intelligent assistive services. Continuous gathering of data will result in huge amounts of data, especially if many...
详细信息
ISBN:
(纸本)9781479944248
Unobtrusive gathering of personal or environmental data using a smartphone can provide the basis for intelligent assistive services. Continuous gathering of data will result in huge amounts of data, especially if many users are involved. Ideally, one might want to keep a large amount of this raw data for future (and maybe different) analysis, and also analyse the data to produce a compact model which can be used in the smartphone for real-time analysis of new data. This motivates a cloud computing solution where data from many users can be stored and analysed efficiently, and then the compact results of the analysis can be downloaded and used in the smartphone. This cloud-based approach is demonstrated using a case study of an activity monitoring application which might be used, for example, to monitor the daily activities, such as walking or going upstairs, of an at-risk person living alone. The cloud-based machine learning uses multiple classification methods, and, starting from individual training sets, enhances and builds classification models for each individual. The cloud-based system also builds a universal model based on all users which can be used as the initial classification model for a new user. The classification model produced by the cloud-based system is downloaded to the smartphone, and can be used to produce accurate real-time activity analysis. As more data is gathered and continually uploaded to the cloud, the models are adapted using an unsupervised learning approach to produce enhanced models which are then downloaded onto the smartphone for improved real-time activity analysis. The evaluation results indicate that the proposed approach can robustly identify activities across multiple individuals: using model adaptation the activity recognition achieves over 95% accuracy in a real usage evaluation.
暂无评论