The impact of photovoltaic self-consumption on the daily electricity demand in Spain: Definition of a model to estimate it.

Introduction: A radical shift in energy production is underway worldwide, replacing fossil fuels with renewable sources and causing structural changes in power generation systems. Problem statement: Photovoltaic installations for self-consumption have experienced a steep increase in recent years. They have reached a significant installed capacity to cause a noticeable reduction in consumption from the national grid, which can cause serious management problems. Objectives: In this work, the evolution of the Spanish demand in the last years is analyzed to identify the influence of self-consumption in the overall demand. In addition, a mathematical model is defined to estimate this influence. Methodology: The demand curves of equivalent days in years with high and low installed self-consumption photovoltaic systems have been compared. Then, an estimation of the electricity generated with this source is proposed, with a mathematical model that takes into account data on solar radiation, installed photovoltaic power for self-consumption and other relevant factors. Results: The analysis of the demand has shown a significant reduction of the electricity demand in daylight hours when the number of self-consumption photovoltaic systems increases. Moreover, the proposed model has been able to provide an estimation of the electricity generated with this source. The addition of these estimates to the actual consumption curves of years with a high number of self-consumption installations gives profiles close to those obtained when self-consumption was low. Recommendation: New storage systems need to be implemented and grid management need to be improved to take advantage of the surpluses produced by photovoltaic systems.

Multi-Step Hourly Power Consumption Forecasting in a Healthcare Building with Recurrent Neural Networks and Empirical Mode Decomposition.

Short-term forecasting of electric energy consumption has become a critical issue for companies selling and buying electricity because of the fluctuating and rising trend of its price. Forecasting tools based on Artificial Intelligence have proved to provide accurate and reliable prediction, especially Neural Networks, which have been widely used and have become one of the preferred ones. In this work, two of them, Long Short-Term Memories and Gated Recurrent Units, have been used along with a preprocessing algorithm, the Empirical Mode Decomposition, to make up a hybrid model to predict the following 24 hourly consumptions (a whole day ahead) of a hospital. Two different datasets have been used to forecast them: a univariate one in which only consumptions are used and a multivariate one in which other three variables (reactive consumption, temperature, and humidity) have been also used. The results achieved show that the best performances were obtained with the multivariate dataset. In this scenario, the hybrid models (neural network with preprocessing) clearly outperformed the simple ones (only the neural network). Both neural models provided similar performances in all cases. The best results (Mean Absolute Percentage Error: 3.51% and Root Mean Square Error: 55.06) were obtained with the Long Short-Term Memory with preprocessing with the multivariate dataset.