A Smart Autonomous Time- and Frequency-Domain Analysis Current Sensor-Based Power Meter Prototype Developed over Fog-Cloud Analytics for Demand-Side Management

Abstract

Electrical energy management, or demand-side management (DSM), in a smart grid is very important for electrical energy savings. With the high penetration rate of the Internet of Things (IoT) paradigm in modern society, IoT-oriented electrical energy management systems (EMSs) in DSM are capable of skillfully monitoring the energy consumption of electrical appliances. While many of today’s IoT devices used in EMSs take advantage of cloud analytics, IoT manufacturers and application developers are devoting themselves to novel IoT devices developed at the edge of the Internet. In this study, a smart autonomous time and frequency analysis current sensor-based power meter prototype, a novel IoT end device, in an edge analytics-based artificial intelligence (AI) across IoT (AIoT) architecture launched with cloud analytics is developed. The prototype has assembled hardware and software to be developed over fog-cloud analytics for DSM in a smart grid. Advanced AI well trained offline in cloud analytics is autonomously and automatically deployed onsite on the prototype as edge analytics at the edge of the Internet for online load identification in DSM. In this study, auto-labeling, or online load identification, of electrical appliances monitored by the developed prototype in the launched edge analytics-based AIoT architecture is experimentally demonstrated. As the proof-of-concept demonstration of the prototype shows, the methodology in this study is feasible and workable.

Internet of things and cloud computing‐based energy management system for demand side management in smart grid

“…Recently we find fog/edge computing-based EMS designs where authors claim that these systems provide benefits of local data processing, cache data management, local resource pooling, load balancing, and delay reduction. [10][11][12] One of the notable works is by Yaghmaee et al who present a combined fog-and-cloud-based system, which utilizes both fog nodes (for local processing) and cloud servers (for reliable data storage and high computing power). They implemented their system on an IoT board with Wi-Fi communication over Constrained Application Protocol (CoAP) and used ThingSpeak open source cloud service.…”

From Intelligent Energy Management to Value Economy through a Digital Energy Currency: Bahrain City Case Study

“…The third component is the use of ICT equipment, which can be any type of smart metering devices, such as real-time energy monitoring, reporting and automation devices [42,43], as well as building management systems. In order to generate the daily BAU scenario for each household, the forecasted values of energy consumption are required.…”

A Parallel Evolutionary Computing-Embodied Artificial Neural Network Applied to Non-Intrusive Load Monitoring for Demand-Side Management in a Smart Home: Towards Deep Learning

“…The preliminaries regarding ANNs and GAs are outlined in Sections 2. feed-forward multi-layer ANN has, the more accurate the neural network is [12]. Deep Neural Networks (NNs) having multiple hidden layers [34][35][36] can be employed, over fogcloud analytics [2,37,38], for NILM in this work. The employed feed-forward ANN, which is structured…”

“…Deep Neural Networks (NNs) having multiple hidden layers [34][35][36] can be employed, over fog-cloud analytics [2,37,38], for NILM in this work. The employed feed-forward ANN, which is structured by three different types of layers including input, hidden, and output layers consists of an interconnected group of artificial neurons with trainable weight coefficients, v qj and w iq , in Figure 4.…”

“…Deep NNs in deep learning have become more attractive AI than ANNs in recent years. In the future, deep NNs having many multiple hidden layers will be investigated and used over fog-cloud analytics [2,37,38] by the developed parallel GA-embodied ANN for NILM in Demand-Side Management (DSM), where distributed GPU (Graphics Processing Unit) computing can be configured to run parallel evolutionary computing to meta-heuristically train a deep NN across multiple CPUs and GPUs on a single computer or a cluster of multiple computers. Acknowledgments: The author would like to sincerely thank the reviewers for their valuable comments and suggestions on this work.…”