The monitoring of power generation installations is key for modelling and predicting their future behaviour. Many renewable energy generation systems, such as photovoltaic panels and wind turbines, strongly depend on weather conditions. However, in situ measurements of relevant weather variables are not always taken into account when designing monitoring systems, and only power output is available. This paper aims to combine data from a Numerical Weather Prediction model with machine learning tools in order to accurately predict the power generation from a photovoltaic system. An Artificial Neural Network (ANN) model is used to predict power outputs from a real installation located in Puglia (southern Italy) using temperature and solar irradiation data taken from the Global Data Assimilation System (GDAS) sflux model outputs. Power outputs and weather monitoring data from the PV installation are used as a reference dataset. Three training and testing scenarios are designed. In the first one, weather data monitoring is used to both train the ANN model and predict power outputs. In the second one, training is done with monitoring data, but GDAS data is used to predict the results. In the last set, both training and result prediction are done by feeding GDAS weather data into the ANN model. The results show that the tested numerical weather model can be combined with machine learning tools to model the output of PV systems with less than 10% error, even when in situ weather measurements are not available.
Street lighting plays an important role in the comfort and safety of drivers and pedestrians, so the control and management of the lighting systems operation and consumption is an essential service for a city. In this document, a methodology is presented to calibrate lighting models in order to assess the lighting performance through simulation techniques. The objective of this calibration is to identify the maintenance factor of the street lamps, determine the real average luminance coefficient of the road pavement and adapt the reflection properties of the road material. The method is applied in three stages and is based on the use of Radiance and GenOpt software suits for the modeling, simulation, and calibration of lighting scenes. The proposed methodology achieves errors as low as 13% for the calculation of illuminance and luminance, evincing its potential to assess the actual lighting conditions of a road.
This document addresses the development of a novel methodology to identify the actual maintenance factor of the luminaires of an outdoor lighting installation in order to assess their lighting performance. The method is based on the combined use of Radiance, a free and open-source tool, for the modeling and simulation of lighting scenes, and GenOpt, a generic optimization program, for the calibration of the model. The application of this methodology allows the quantification of the deterioration of the road lighting system and the identification of luminaires that show irregularities in their operation. Values lower than 9% for the error confirm that this research can contribute to the management of street lighting by assessing real road conditions.
Collective self-consumption (CSC) systems offer a great opportunity to increase the viability of photovoltaic installations by reducing costs and increasing profitability for consumers. In addition, CSC systems increase self-sufficiency (SS) and self-consumption (SC). These systems require a proper energy allocation strategy (EAS) to define the energy distribution within the CSC. However, most EASs do not analyze the individual impact of the rules and mechanisms adopted. Therefore, six different EASs are proposed and evaluated in terms of both collective and individual cost, SC, and SS. The results show that the EASs based on minimizing collective costs are the most beneficial for the community, although they imply an unfair distribution of energy among users. On the other hand, the other EASs proposed stand out for reaching an equilibrium in terms of cost, SS, and SC, although the collective profitability is lower. The best results are achieved considering dynamic coefficients, which are preferred over static ones.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.