Predicting Energy Consumption Through Machine Learning Using a Smart-Metering Architecture
| Autor: | George Koronias, Stelios Koutroubinas, Paraskevas Deligiannis |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
business.industry
Computer science 020209 energy Strategy and Management Scale (chemistry) 02 engineering and technology Energy consumption Education Wide area network 0202 electrical engineering electronic engineering information engineering Wireless 020201 artificial intelligence & image processing Metering mode Electrical and Electronic Engineering Architecture Ubiquitous network business Remote management Computer network |
| Zdroj: | IEEE Potentials. 38:29-34 |
| ISSN: | 1558-1772 0278-6648 |
| DOI: | 10.1109/mpot.2018.2852564 |
| Popis: | Extensive Internet of Things (IoT) networks consisting of billions of smart interconnected devices can serve a plethora of functions. The scale of these networks poses several architectural challenges, especially when combined with the essential requirements of reliable device telemetry, automated remote management, and multilayer security. In this article, we outline a flexible smart-metering architecture that can provide device monitoring and management in a unified manner over disparate underlying network technologies, such as nar row-band IoT (NB-IoT), LTECat- M1, Zigbee, Wi-Fi, Wireless Smart Ubiquitous Network (Wi-SUN), longrange wide area network (LoRaWAN), and Sigfox. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|