Enabling Artificial Intelligent Virtual Sensors in an IoT Environment

Abstract

The demands for a large number of sensors increase as the proliferation of Internet of Things (IoT) and smart cities applications are continuing at a rapid pace. This also increases the cost of the infrastructure and the installation and maintenance overhead and creates significant performance degradation in the end-to-end communication, monitoring, and orchestration of the various connected devices. In order to solve the problem of increasing sensor demands, this paper suggests replacing physical sensors with machine learning (ML) models. These software-based artificial intelligence models are called virtual sensors. Extensive research and simulation comparisons between fourteen ML models provide a solid ground decision when it comes to the selection of the most accurate model to replace physical sensors, such as temperature and humidity sensors. In this problem at hand, the virtual and physical sensors are designed to be scattered in a smart home, while being connected and run on the same IoT platform. Thus, this paper also introduces a custom lightweight IoT platform that runs on a Raspberry Pi equipped with physical temperature and humidity sensors, which may also execute the virtual sensors. The evaluation results of the devised virtual sensors in a smart home scenario are promising and corroborate the applicability of the proposed methodology.

A Survey of AI Techniques in IoT Applications with Use Case Investigations in the Smart Environmental Monitoring and Analytics in Real-Time IoT Platform

“…It allows the platform to support the combination of multiple AI models into a single dataflow process. Then, in [84], Stavropoulos et al introduced the integration of machine learning into the IoT platform to create virtual sensors to replace physical sensors.…”

Real-time Monitoring of Cable Sag and Overhead Line Parameters Based on a Distributed Sensor Network and Implementation in a Web server and IoT

“…The main components of SCADA systems are one or more servers and clients. The servers used in this system are of the Open Platform Communications (OPC) type, which aims to define a common interface that requires only one design stage and then multiple reuses for any other SCADA project or other software packages [23][24][25].…”

“…It is a relational database management system based on the clientserver model using the SQL language. MySQL's features include: multi-threaded and multi-processor operation, functionality on a wide range of operating systems, support for large databases, and a high level of security based on a flexible and secure system of passwords and privileges [23][24][25]. The use of Open Database Connectivity (ODBC) makes it easy for the OPL cable condition monitoring process application program to write to and query the MySQL server database.…”

“…A Web client, such as a browser, exchanges data with a Web service by sending an HTTP request to a specific Uniform Resource Locator (URL) address, whereas the LabVIEW embedded Web server maps a URL to each HTTP VI method, so that the specific URL used by the client determines which HTTP VI method receives and resolves the HTTP request. The request contains values for assigning specific parameters in the HTTP GET method, and after each request, the HTTP GET method processes these values and returns a response [24,25].…”

“…Establishing alternative calculation methods and verification calculation relations for the OPL cable sag calculation depending on the groups of sensors used, thus obtaining a software method for detecting the failure of a sensor, a method whose usefulness can be expressed in terms of increasing system reliability;  Establishing the hardware and software architecture of the OPL online cable monitoring application;  Se ing up the necessary configurations for data transmission using ModBUS [20] and ZigBee [21] protocols in order to minimise energy consumption in the process of local centralisation of data from sensors and transmission via Global System for Mobile Communications (GSM) [22] to the user server;  Implementation of the software module for reading quantities from the sensor network through a ModBUS I/O server;  Implementation of the software module for the real-time calculation of the OPL cable sag and monitoring of the parameters of interest of the power line, including the correct functioning of the sensors and maintenance within the acceptance limits of the OPL cable sag values;  Implementation of a software module to send automatic e-mails with warnings and alarms regarding OPL cable sag limits and sensor faults;  Implementation of the software module for the transfer of data to the user's Internet via a web server [23,24];  Implementation of the software module for viewing data by authorised users, based on user and password, via an IoT server [25].…”