A Neural Network Based Intelligent Predictive Sensor for Cloudiness, Solar Radiation and Air Temperature

Pedro M Ferreira,Igor A C Martins,António E Ruano,João M Gomes

doi:10.3390/s121115750

Abstract

Accurate measurements of global solar radiation and atmospheric temperature, as well as the availability of the predictions of their evolution over time, are important for different areas of applications, such as agriculture, renewable energy and energy management, or thermal comfort in buildings. For this reason, an intelligent, light-weight and portable sensor was developed, using artificial neural network models as the time-series predictor mechanisms. These have been identified with the aid of a procedure based on the multi-objective genetic algorithm. As cloudiness is the most significant factor affecting the solar radiation reaching a particular location on the Earth surface, it has great impact on the performance of predictive solar radiation models for that location. This work also represents one step towards the improvement of such models by using ground-to-sky hemispherical colour digital images as a means to estimate cloudiness by the fraction of visible sky corresponding to clouds and to clear sky. The implementation of predictive models in the prototype has been validated and the system is able to function reliably, providing measurements and four-hour forecasts of cloudiness, solar radiation and air temperature.

Highlights

Nowadays there is a global need for decreasing our energy consumption, to ensure that what we get from our natural resources is efficiently used, and that we live in balance with the environment
Testing and validation was performed firstly by comparing the results obtained by the prototype to those obtained on a laboratory computer, using the same input data
For solar radiation and air temperature, the reference was given by a Delta-T weather station installed a few meters away from the Total Sky Imager (TSI) and the prototype

Summary

Introduction

Nowadays there is a global need for decreasing our energy consumption, to ensure that what we get from our natural resources is efficiently used, and that we live in balance with the environment. A major field of research consists in developing intelligent systems capable of integrating environmental data, to improve efficiency in the utilisation of resources and to enable sustainable functioning of man-made utilities. The main focus is on global solar radiation, as it influences the majority of living beings in many different ways. The authors have successfully employed predictive models of solar radiation, air temperature and relative humidity in order to improve the optimisation of energy consumption by Heating Ventilation and Air Conditioning devices and to maintain thermal comfort in public buildings [1,2,3]

Methods

Results

Conclusion