Search

Aiming at the problem that power load data are stochastic and that it is difficult to obtain accurate forecasting results by a single algorithm, in this paper, a combined forecasting method for short-term power load was proposed based on the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN)-sample entropy (SE), the BP neural network (BPNN), and the Transformer model. Firstly, the power load data were decomposed into several power load subsequences with obvious complexity differences by using the CEEMDAN-SE. Then, BPNN and Transformer model were used to forecast the subsequences with low complexity and the subsequences with high complexity, respectively. Finally, the forecasting results of each subsequence were superimposed to obtain the final forecasting result. The simulation was taken from our proposed model and six forecasting models by using the load dataset from a certain area of Spain. The results showed that the MAPE of our proposed CEEMDAN-SE-BPNN-Transformer model was 1.1317%, while the RMSE was 304.40, which was better than the selected six forecasting models. [ABSTRACT FROM AUTHOR]

Assessing the training process of artificial neural networks (ANNs) is vital for enhancing their performance and broadening their applicability. This paper employs the Monte Carlo simulation (MCS) technique, integrated with a stopping criterion, to construct the probability distribution of the learning error of an ANN designed for short-term forecasting. The training and validation processes were conducted multiple times, each time considering a unique random starting point, and the subsequent forecasting error was calculated one step ahead. From this, we ascertained the probability of having obtained all the local optima. Our extensive computational analysis involved training a shallow feedforward neural network (FFNN) using wind power and load demand data from the transmission systems of the Netherlands and Germany. Furthermore, the analysis was expanded to include wind speed prediction using a long short-term memory (LSTM) network at a site in Spain. The improvement gained from the FFNN, which has a high probability of being the global optimum, ranges from 0.7% to 8.6%, depending on the forecasting variable. This solution outperforms the persistent model by between 5.5% and 20.3%. For wind speed predictions using an LSTM, the improvement over an average-trained network stands at 9.5%, and is 6% superior to the persistent approach. These outcomes suggest that the advantages of exhaustive search vary based on the problem being analyzed and the type of network in use. The MCS method we implemented, which estimates the probability of identifying all local optima, can act as a foundational step for other techniques like Bayesian model selection, which assumes that the global optimum is encompassed within the available hypotheses. [ABSTRACT FROM AUTHOR]

Aerobiological predictive model development is of increasing interest, despite the distribution and variability of data and the limitations of statistical methods making it highly challenging. The use of concentration thresholds and models, where a binary response allows one to establish the occurrence or non-occurrence of the threshold, have been proposed to reduce difficulties. In this paper, we use logistic regression (logit) and regression trees to predict the daily concentration thresholds (low, medium, high, and very high) of six airborne fungal spore taxa (Alternaria, Cladosporium, Agaricus, Ganoderma, Leptosphaeria, and Pleospora) in eight localities in Catalonia (NE Spain) using data from 1995 to 2014. The predictive potential of these models was analyzed through sensitivity and specificity. The models showed similar results regarding the relationship and influence of the meteorological parameters and fungal spores. Ascospores showed a strong relationship with precipitation and basidiospores with minimum temperature, while conidiospores did not indicate any preferences. Sensitivity (true-positive) and specificity (false-positive) presented highly satisfactory validation results for both models in all thresholds, with an average of 73%. However, seeing as logit offers greater precision when attempting to establish the exceedance of a concentration threshold and is easier to apply, it is proposed as the best predictive model. [ABSTRACT FROM AUTHOR]

Accurate solar forecasting lately relies on advances in the field of artificial intelligence and on the availability of databases with large amounts of information on meteorological variables. In this paper, we present the methodology applied to introduce a large-scale, public, and solar irradiance dataset, CyL-GHI, containing refined data from 37 stations found within the Spanish region of Castile and León (Spanish: Castilla y León, or CyL). In addition to the data cleaning steps, the procedure also features steps that enable the addition of meteorological and geographical variables that complement the value of the initial data. The proposed dataset, resulting from applying the processing methodology, is delivered both in raw format and with the quality processing applied, and continuously covers 18 years (the period from 1 January 2002 to 31 December 2019), with a temporal resolution of 30 min. CyL-GHI can result in great importance in studies focused on the spatial-temporal characteristics of solar irradiance data, due to the geographical information considered that enables a regional analysis of the phenomena (the 37 stations cover a land area larger than 94,226 km2). Afterwards, three popular artificial intelligence algorithms were optimised and tested on CyL-GHI, their performance values being offered as baselines to compare other forecasting implementations. Furthermore, the ERA5 values corresponding to the studied area were analysed and compared with performance values delivered by the trained models. The inclusion of previous observations of neighbours as input to an optimised Random Forest model (applying a spatio-temporal approach) improved the predictive capability of the machine learning models by almost 3%. Dataset:  https://doi.org/10.5281/zenodo.7404167 Dataset License: CC-BY-SA-NC [ABSTRACT FROM AUTHOR]

In this paper, we propose different explicable forecasting approaches, based on inductive and evolutionary decision rules, for extreme low-visibility events prediction. Explicability of the processes given by the rules is in the core of the proposal. We propose two different methodologies: first, we apply the PRIM algorithm and evolution to obtain induced and evolved rules, and subsequently these rules and boxes of rules are used as a possible simpler alternative to ML/DL classifiers. Second, we propose to integrate the information provided by the induced/evolved rules in the ML/DL techniques, as extra inputs, in order to enrich the complex ML/DL models. Experiments in the prediction of extreme low-visibility events in Northern Spain due to orographic fog show the good performance of the proposed approaches. [ABSTRACT FROM AUTHOR]

Soiling of PV modules is an issue causing non-negligible losses on PV power plants, between 3 and 4% of the total energy production. Cleaning is the most common way to mitigate soiling. The impact of the cleaning activity can be significant, both in terms of cost and resources consumption. For these reasons, it is important to monitor and predict soiling profiles and establish an optimal cleaning schedule. Especially in locations where raining is irregular or where desert winds carry a high concentration of particles, it is also important to know how precipitation and dust events affect the soiling ratio. This paper presents a new model based on environmental conditions that helps the decision-making process of the cleaning schedule. The model was validated by the analysis of five large grid-connected PV plants in Spain over two years of operation, with a total power of 200 MW. The comparison between the model and soiling sensors at the five locations was included. Excellent results were achieved, the mean difference between sensors and model being 0.71%. [ABSTRACT FROM AUTHOR]

In this paper, the fractional-order generalization of the susceptible-infected-recovered (SIR) epidemic model for predicting the spread of the COVID-19 disease is presented. The time-domain model implementation is based on the fixed-step method using the nabla fractional-order difference defined by Grünwald-Letnikov formula. We study the influence of fractional order values on the dynamic properties of the proposed fractional-order SIR model. In modeling the COVID-19 transmission, the model's parameters are estimated while using the genetic algorithm. The model prediction results for the spread of COVID-19 in Italy and Spain confirm the usefulness of the introduced methodology. [ABSTRACT FROM AUTHOR]

The evolution of some epidemics, such as influenza, demonstrates common patterns both in different regions and from year to year. On the contrary, epidemics such as the novel COVID-19 show quite heterogeneous dynamics and are extremely susceptible to the measures taken to mitigate their spread. In this paper, we propose empirical dynamic modeling to predict the evolution of influenza in Spain's regions. It is a non-parametric method that looks into the past for coincidences with the present to make the forecasts. Here, we extend the method to predict the evolution of other epidemics at any other starting territory and we also test this procedure with Spanish COVID-19 data. We finally build influenza and COVID-19 networks to check possible coincidences in the geographical distribution of both diseases. With this, we grasp the uniqueness of the geographical dynamics of COVID-19. [ABSTRACT FROM AUTHOR]

Accurate wind power prediction can increase the utilization rate of wind power generation and maintain the stability of the power system. At present, a large number of wind power prediction studies are based on the mean square error (MSE) loss function, which generates many errors when predicting original data with random fluctuation and non-stationarity. Therefore, a hybrid model for wind power prediction named IVMD-FE-Ad-Informer, which is based on Informer with an adaptive loss function and combines improved variational mode decomposition (IVMD) and fuzzy entropy (FE), is proposed. Firstly, the original data are decomposed into K subsequences by IVMD, which possess distinct frequency domain characteristics. Secondly, the sub-series are reconstructed into new elements using FE. Then, the adaptive and robust Ad-Informer model predicts new elements and the predicted values of each element are superimposed to obtain the final results of wind power. Finally, the model is analyzed and evaluated on two real datasets collected from wind farms in China and Spain. The results demonstrate that the proposed model is superior to other models in the performance and accuracy on different datasets, and this model can effectively meet the demand for actual wind power prediction. [ABSTRACT FROM AUTHOR]

Due to the relevant penetration of solar PV power plants, an accurate power generation forecasting of these installations is crucial to provide both reliability and stability of current grids. At the same time, PV monitoring requirements are more and more demanded by different agents to provide reliable information regarding performances, efficiencies, and possible predictive maintenance tasks. Under this framework, this paper proposes a methodology to evaluate different LoRa-based PV monitoring architectures and node layouts in terms of short-term solar power generation forecasting. A random forest model is proposed as forecasting method, simplifying the forecasting problem especially when the time series exhibits heteroscedasticity, nonstationarity, and multiple seasonal cycles. This approach provides a sensitive analysis of LoRa parameters in terms of node layout, loss of data, spreading factor and short time intervals to evaluate their influence on PV forecasting accuracy. A case example located in the southeast of Spain is included in the paper to evaluate the proposed analysis. This methodology is applicable to other locations, as well as different LoRa configurations, parameters, and networks structures; providing detailed analysis regarding PV monitoring performances and short-term PV generation forecasting discrepancies. [ABSTRACT FROM AUTHOR]

The Galician coast (NW Spain) is a region that is strongly influenced by the presence of low pressure systems in the mid-Atlantic Ocean and the periodic passage of storms that give rise to severe sea states. Since its wave climate is one of the most energetic in Europe, the objectives of this paper were twofold. The first objective was to characterize the most extreme wave height events in Galicia over the wintertime of a two-year period (2015-2016) by using reliable high-frequency radar wave parameters in concert with predictions from a regional wave (WAV) forecasting system running operationally in the Iberia-Biscay-Ireland (IBI) area, denominated IBI-WAV. The second objective was to showcase the application of satellite wave altimetry (in particular, remote-sensed three-hourly wave height estimations) for the daily skill assessment of the IBI-WAV model product. Special attention was focused on monitoring Ophelia-one of the major hurricanes on record in the easternmost Atlantic-during its 3-day track over Ireland and the UK (15-17 October 2017). Overall, the results reveal the significant accuracy of IBI-WAV forecasts and prove that a combined observational and modeling approach can provide a comprehensive characterization of severe wave conditions in coastal areas and shows the benefits from the complementary nature of both systems. [ABSTRACT FROM AUTHOR]

Accurately forecasting energy metrics is essential for efficiently managing renewable energy generation. Given the high variability in load and renewable energy power output, this represents a crucial area of research in order to pave the way for increased adoption of low-carbon energy solutions. Whilst the impact of different neural network architectures and algorithmic approaches has been researched extensively, the impact of utilising additional weather variables in forecasts have received far less attention. This article demonstrates that weather variables can have a significant influence on energy forecasting and presents methodologies for using these variables within a long short-term memory (LSTM) architecture to achieve improvements in forecasting accuracy. Moreover, we introduce the use of the seasonal components of the target time series, as exogenous variables, that are also observed to increase accuracy. Load, solar and wind generation time series were forecast one hour ahead using an LSTM architecture. Time series data were collected in five Spanish cities and aggregated for analysis, alongside five exogenous weather variables, also recorded in Spain. A variety of LSTM architectures and hyperparameters were investigated. By tuning exogenous weather variables, a 33% decrease in mean squared error was observed for solar generation forecasting. A 22% decrease in mean absolute squared error (MASE), compared to 24-h ahead forecasts made by the Transmission Service Operator (TSO) in Spain, was also observed for solar generation. Compared to using the target variable in isolation, utilising exogenous weather variables decreased MASE by approximately 10%, 15% and 12% for load, solar and wind generation, respectively. By using the seasonal component of the target variables as an exogenous variable itself, we demonstrated decreases in MASE of 19%, 12% and 8% for load, solar and wind generation, respectively. These results emphasise the significant benefits of incorporating weather and seasonal components into energy-related time series forecasts. [ABSTRACT FROM AUTHOR]

Predicting the levels of a pollutant in a given area is an open problem, mainly because historical data are typically available at certain locations, where monitoring stations are located, but not at all locations in the area. This work presents an approach based on developing predictions at each of the points where an immission station is available; in this case, based on shallow Artificial Neural Networks, ANNs, and then using a simple geostatistical interpolation algorithm (Inverse Distance Weighted, IDW), a pollutant map is constructed over the entire study area, thus providing predictions at each point in the plane. The ANN models are designed to make 1 h ahead and 4 h ahead predictions, using an autoregressive scheme as inputs (in the case of 4 h ahead as a jumping strategy). The results are then compared using the Friedman and Bonferroni tests to select the best model at each location, and predictions are made with all the best models. In general, to the 1 h ahead prediction models, the optimal models typically have fewer neurons and require minimal historical data. For instance, the best model in Algeciras has an R of almost 0.89 and consists of 1 hidden neuron and 3 to 5 lags, similar to Colegio Los Barrios. In the case of 4h ahead prediction, Colegio Carteya station shows the best model, with an R of almost 0.89 and a MSE of less than 240, including 5 hidden neurons and different lags from the past. The results are sufficiently adequate, especially in the case of predictions 4 h into the future. The aim is to integrate the models into a tool for citizens and administrations to make decisions. [ABSTRACT FROM AUTHOR]

This paper presents long- and short-term analyses and predictions of dammed water level in a hydropower reservoir. The long-term analysis was carried out by using techniques such as detrended fluctuation analysis, auto-regressive models, and persistence-based algorithms. On the other hand, the short-term analysis of the dammed water level in the hydropower reservoir was modeled as a prediction problem, where machine learning regression techniques were studied. A set of models, including different types of neural networks, Support Vector regression, or Gaussian processes was tested. Real data from a hydropower reservoir located in Galicia, Spain, qwew considered, together with predictive variables from upstream measuring stations. We show that the techniques presented in this paper offer an excellent tool for the long- and short-term analysis and prediction of dammed water level in reservoirs for hydropower purposes, especially important for the management of water resources in areas with hydrology stress, such as Spain. [ABSTRACT FROM AUTHOR]

Two important aspects of global environmental problems are that (1) the actions of past generations affect the opportunities of the present, and (2) both in the past and the present generations, collaboration across different countries is needed to provide global public goods. In this paper, we study how these two aspects influence public good provisions by running simultaneous intercountry laboratory experiments using a modified public goods game in Denmark, Spain and Ghana. While the theoretical predictions of the modified public goods game do not differ from that of the standard public goods game, our experimental results show otherwise. Pooling across results from our Danish, Spanish and Ghanaian participants, we find that present-generation individuals contribute a higher percentage of their endowments when they have better institutions and a lower percentage of their endowments when they have higher endowments. We also find that present-generation individuals contribute less to transnational public goods only when their initial conditions have not been affected by past-generation contributions. [ABSTRACT FROM AUTHOR]

The development of Short-Term Forecasting Techniques has a great importance for power system scheduling and managing. Therefore, many recent research papers have dealt with the proposal of new forecasting models searching for higher efficiency and accuracy. Several kinds of artificial intelligence (AI) techniques have provided good performance at predicting and their efficiency mainly depends on the characteristics of the time series data under study. Load forecasting has been widely studied in recent decades and models providing mean absolute percentage errors (MAPEs) below 5% have been proposed. On the other hand, short-term generation forecasting models for photovoltaic plants have been more recently developed and the MAPEs are in general still far from those achieved from load forecasting models. The aim of this paper is to propose a methodology that could help power systems or aggregators to make up for the lack of accuracy of the current forecasting methods when predicting renewable energy generation. The proposed methodology is carried out in three consecutive steps: (1) short-term forecasting of energy consumption and renewable generation; (2) classification of daily pattern for the renewable generation data using Dynamic Time Warping; (3) application of Demand Response strategies using Physically Based Load Models. Real data from a small town in Spain were used to illustrate the performance and efficiency of the proposed procedure. [ABSTRACT FROM AUTHOR]

The rapid expansion of solar photovoltaic (PV) generation has established its pivotal role in the shift toward sustainable energy systems. This study conducts an in-depth analysis of solar generation data from 2015 to 2018 in Spain, with a specific emphasis on temporal patterns, excluding weather data. Employing the powerful eXtreme gradient boosting (XGBoost) algorithm for modeling and forecasting, our research underscores its exceptional efficacy in capturing solar generation trends, as evidenced by a remarkable root mean squared error (RMSE) of 11.042, a mean absolute error (MAE) of 5.621, an R-squared (R²) of 0.999, and a minimal mean absolute percentage error (MAPE) of 0.046. These insights hold substantial implications for grid management, energy planning, and policy development, reaffirming solar energy's promise as a dependable and sustainable contributor to the electrical power system's evolution. This research contributes to the growing body of knowledge aimed at optimizing renewable energy integration and enhancing energy sustainability for future generations. [ABSTRACT FROM AUTHOR]

In this study, we utilized three different indices to assess drought conditions in the Doñana National Park (DNP) located in southern Spain. These indices included the Standardized Precipitation Index (SPI), which is based on precipitation statistics, the Standardized Precipitation Evapotranspiration Index (SPEI), which incorporates both precipitation and air temperature data, and the Groundwater Recharge Drought Index (GRDI), a newly developed index specifically designed to evaluate groundwater drought. The analysis covered the time period from 1985 to 2015, and future projections were made for the years 2030–2060 under different climate scenarios (RCP 4.5 and RCP 8.5). Our findings revealed a significant decrease in total precipitation of approximately 13–14% compared to historical records (1985–2015). Moreover, severely to extremely wet periods exhibited a reduction ranging from 25% to 38%. A key contribution of this study is the application of the GRDI index, which allowed us to assess groundwater recharge rates. We observed a decline in the simulated mean recharge rates during the 21st century when compared to the historical period spanning from 1950 to 2009. This decline can be attributed to increased evapotranspiration. The results of this research provide valuable insights for the Spanish water resources administration. The observed reductions in precipitation and groundwater recharge rates emphasize the need for appropriate mitigation measures. The findings will aid the administration in formulating an integrated water resources management strategy in the Doñana National Park and its surrounding basin. By understanding the projected changes in drought conditions, the administration can make informed decisions to ensure sustainable water resource management in the region. [ABSTRACT FROM AUTHOR]

Thermostatic load control systems are widespread in many countries. Since they provide heat for domestic hot water and space heating on a massive scale in the residential sector, the assessment of their energy performance and the effect of different control strategies requires simplified modeling techniques demanding a small number of inputs and low computational resources. Data-driven techniques are envisaged as one of the best options to meet these constraints. This paper presents a novel methodology consisting of the combination of an optimization algorithm, two auto-regressive models and a control loop algorithm able to virtually replicate the control of thermostatically driven systems. This combined strategy includes all the thermostatically controlled modes governed by the set point temperature and enables automatic assessment of the energy consumption impact of multiple scenarios. The required inputs are limited to available historical readings from smart thermostats and external climate data sources. The methodology has been trained and validated with data sets coming from a selection of 11 smart thermostats, connected to gas boilers, placed in several households located in north-eastern Spain. Important conclusions of the research are that these techniques can estimate the temperature decay of households when the space heating is off as well as the energy consumption needed to reach the comfort conditions. The results of the research also show that estimated median energy savings of 18.1% and 36.5% can be achieved if the usual set point temperature schedule is lowered by 1 °C and 2 °C, respectively. [ABSTRACT FROM AUTHOR]

This paper presents a methodology to calculate day-ahead wind speed predictions based on historical measurements done by weather stations. The methodology was tested for three locations: Colombia, Ecuador, and Spain. The data is input into the process in two ways: (1) As a single time series containing all measurements, and (2) as twenty-four separate parallel sequences, corresponding to the values of wind speed at each of the 24 h in the day over several months. The methodology relies on the use of three non-parametric techniques: Least-squares support vector machines, empirical mode decomposition, and the wavelet transform. Moreover, the traditional and simple auto-regressive model is applied. The combination of the aforementioned techniques results in nine methods for performing wind prediction. Experiments using a matlab implementation showed that the least-squares support vector machine using data as a single time series outperformed the other combinations, obtaining the least root mean square error (RMSE). [ABSTRACT FROM AUTHOR]

Due to the rise of new technologies, further development of digital competence by professors is necessary. The aim of this paper is to know the pedagogical digital competence of lecturers in Spain, focused on a model called PDC-TER: ICT resources to Teach, to Evaluate and to Research; as well as to predict those variables that affect the level of this competence through different regressions (Multiple Linear Regression, MLR). A study has been carried out in the Spanish territory, with a total of 867 lecturers. For it, an ex post facto non-probabilistic study based on the survey technique has been proposed. The results show that the professors have an average level of digital pedagogical competence, while in the 2.0 tools for teaching and research dimensions, it has a medium high level of competence, as well as a medium level in relation to the use of tools 2.0 for the evaluation. Furthermore, one of the variables predictive of the level of digital competence in the three dimensions of the PDC-TER model, is the number of research and innovation projects in which they have participated. These data highlight the need to improve the digital competence of professors in order to meet the demands of the qualified professions of the future, and therefore, prepare students for it. [ABSTRACT FROM AUTHOR]

This paper presents a novel methodology for Climate Network (CN) construction based on the Kullback-Leibler divergence (KLD) among Membership Probability (MP) distributions, obtained from the Second Order Data-Coupled Clustering (SODCC) algorithm. The proposed method is able to obtain CNs with emergent behaviour adapted to the variables being analyzed, and with a low number of spurious or missing links. We evaluate the proposed method in a problem of CN construction to assess differences in wind speed prediction at different wind farms in Spain. The considered problem presents strong local and mesoscale relationships, but low synoptic scale relationships, which have a direct influence in the CN obtained. We carry out a comparison of the proposed approach with a classical correlation-based CN construction method. We show that the proposed approach based on the SODCC algorithm and the KLD constructs CNs with an emergent behaviour according to underlying wind speed prediction data physics, unlike the correlation-based method that produces spurious and missing links. Furthermore, it is shown that the climate network construction method facilitates the evaluation of symmetry properties in the resulting complex networks. [ABSTRACT FROM AUTHOR]

Accurate and rapid forecasting of short-term loads facilitates demand-side management by electricity retailers. The complexity of customer demand makes traditional forecasting methods incapable of meeting the accuracy requirements, so a self-attention based short-term load forecasting (STLF) considering demand-side management is proposed. In the data preprocessing stage, non-parametric kernel density estimation is used to construct customer electricity consumption feature curves, and then historical load data are used to delineate the feasible domain range for outlier detection. In the feature selection stage, the feature data are selected using variational modal decomposition and a maximum information coefficient to enhance the model prediction accuracy. In the model prediction stage, the decomposed intrinsic mode function components are independently predicted and reconstructed using an Informer based on improved self-attention. Additionally, the novel AdaBlief optimizer is used to optimize the model parameters. Cross-sectional and longitudinal experiments are conducted on a regional-level load dataset set in Spain. The experimental results prove that the proposed method is superior to other methods in STLF. [ABSTRACT FROM AUTHOR]

Time series forecasting of passenger demand is crucial for optimal planning of limited resources. For smart cities, passenger transport in urban areas is an increasingly important problem, because the construction of infrastructure is not the solution and the use of public transport should be encouraged. One of the most sophisticated techniques for time series forecasting is Long Short Term Memory (LSTM) neural networks. These deep learning models are very powerful for time series forecasting but are not interpretable by humans (black-box models). Our goal was to develop a predictive and linguistically interpretable model, useful for decision making using large volumes of data from different sources. Our case study was one of the most demanded bus lines of Madrid. We obtained an interpretable model from the LSTM neural network using a surrogate model and the 2-tuple fuzzy linguistic model, which improves the linguistic interpretability of the generated Explainable Artificial Intelligent (XAI) model without losing precision. [ABSTRACT FROM AUTHOR]

Featured Application: Featured Application: Several commercially available and free downloadable PV modelling software tools are compared with real data for three different photovoltaic power plants in operation over the past 12 years. Both annual and monthly results are analyzed. Prediction of energy production is crucial for the design and installation of PV plants. In this study, five free and commercial software tools to predict photovoltaic energy production are evaluated: RETScreen, Solar Advisor Model (SAM), PVGIS, PVSyst, and PV*SOL. The evaluation involves a comparison of monthly and annually predicted data on energy supplied to the national grid with real field data collected from three real PV plants. All the systems, located in Castile and Leon (Spain), have three different tilting systems: fixed mounting, horizontal-axis tracking, and dual-axis tracking. The last 12 years of operating data, from 2008 to 2020, are used in the evaluation. Although the commercial software tools were easier to use and their installations could be described in detail, their results were not appreciably superior. In annual global terms, the results hid poor estimations throughout the year, where overestimations were compensated by underestimated results. This fact was reflected in the monthly results: the software yielded overestimates during the colder months, while the models showed better estimates during the warmer months. In most studies, the deviation was below 10% when the annual results were analyzed. The accuracy of the software was also reduced when the complexity of the dual-axis solar tracking systems replaced the fixed installation. [ABSTRACT FROM AUTHOR]

Gender-Based Violence (GBV) is a serious problem that societies and governments must address using all applicable resources. This requires adequate planning in order to optimize both resources and budget, which demands a thorough understanding of the magnitude of the problem, as well as analysis of its past impact in order to infer future incidence. On the other hand, for years, the rise of Machine Learning techniques and Big Data has led different countries to collect information on both GBV and other general social variables that in one way or another can affect violence levels. In this work, in order to forecast GBV, firstly, a database of features related to more than a decade's worth of GBV is compiled and prepared from official sources available due to Spain's open access. Then, secondly, a methodology is proposed that involves testing different methods of features selection so that, with each of the subsets generated, four techniques of predictive algorithms are applied and compared. The tests conducted indicate that it is possible to predict the number of GBV complaints presented to a court at a predictive horizon of six months with an accuracy (Root Median Squared Error) of 0.1686 complaints to the courts per 10,000 inhabitants—throughout the whole Spanish territory—with a Multi-Objective Evolutionary Search Strategy for the selection of variables, and with Random Forest as the predictive algorithm. The proposed methodology has also been successfully applied to three specific Spanish territories of different populations (large, medium, and small), pointing to the presented method's possible use elsewhere in the world. [ABSTRACT FROM AUTHOR]

Accurate prediction of building indoor temperatures and thermal demand is of great help to control and optimize the energy performance of a building. However, building thermal inertia and lag lead to complex nonlinear systems is difficult to model. In this context, the application of artificial neural networks (ANNs) in buildings has grown considerably in recent years. The aim of this work is to study the thermal inertia of a building by developing an innovative methodology using multi-layered perceptron (MLP) and long short-term memory (LSTM) neural networks. This approach was applied to a public library building located in the north of Spain. A comparison between the prediction errors according to the number of time lags introduced in the models has been carried out. Moreover, the accuracy of the models was measured using the CV(RMSE) as advised by AHSRAE. The main novelty of this work lies in the analysis of the building inertia, through machine learning algorithms, observing the information provided by the input of time lags in the models. The results of the study prove that the best models are those that consider the thermal lag. Errors below 15% for thermal demand and below 2% for indoor temperatures were achieved with the proposed methodology. [ABSTRACT FROM AUTHOR]

Currently, there is great interest in reducing the consumption of fossil fuels (and other non-renewable energy sources) in order to preserve the environment; smart buildings are commonly proposed for this purpose as they are capable of producing their own energy and using it optimally. However, at times, solar energy is not able to supply the energy demand fully; it is mandatory to know the quantity of energy needed to optimize the system. This research focuses on the prediction of output temperature from a solar thermal collector. The aim is to measure solar thermal energy and optimize the energy system of a house (or building). The dataset used in this research has been taken from a real installation in a bio-climate house located on the Sotavento Experimental Wind Farm, in north-west Spain. A hybrid intelligent model has been developed by combining clustering and regression methods such as neural networks, polynomial regression, and support vector machines. The main findings show that, by dividing the dataset into small clusters on the basis of similarity in behavior, it is possible to create more accurate models. Moreover, combining different regression methods for each cluster provides better results than when a global model of the whole dataset is used. In temperature prediction, mean absolute error was lower than 4 ∘ C. [ABSTRACT FROM AUTHOR]

Electricity management and production depend heavily on demand forecasts made. Any mismatch between the energy demanded with respect to that produced supposes enormous losses for the consumer. Transmission System Operators use time series-based tools to forecast accurately the future demand and set the production program. One of the most effective and highly used methods are Holt-Winters. Recently, the incorporation of the multiple seasonal Holt-Winters methods has improved the accuracy of the predictions. These forecasts, depend greatly on the parameters with which the model is constructed. The forecasters need to deal with these parameters values when operating the model. In this article, the parameters space of the multiple seasonal Holt-Winters models applied to electricity demand in Spain is analysed and discussed. The parameters stability analysis leads to forecasters better understanding the behaviour of the predictions and managing their exploitation efficiently. The analysis addresses different time windows, depending on the period of the year as well as different training set sizes. The results show the influence of the calendar effect on these parameters and if it is necessary or not to update them in order to obtain a good accuracy over time. [ABSTRACT FROM AUTHOR]

Featured Application: Energy demand forecasting to improve power generation management. Modern energy systems collect high volumes of data that can provide valuable information about energy consumption. Electric companies can now use historical data to make informed decisions on energy production by forecasting the expected demand. Many deep learning models have been proposed to deal with these types of time series forecasting problems. Deep neural networks, such as recurrent or convolutional, can automatically capture complex patterns in time series data and provide accurate predictions. In particular, Temporal Convolutional Networks (TCN) are a specialised architecture that has advantages over recurrent networks for forecasting tasks. TCNs are able to extract long-term patterns using dilated causal convolutions and residual blocks, and can also be more efficient in terms of computation time. In this work, we propose a TCN-based deep learning model to improve the predictive performance in energy demand forecasting. Two energy-related time series with data from Spain have been studied: the national electric demand and the power demand at charging stations for electric vehicles. An extensive experimental study has been conducted, involving more than 1900 models with different architectures and parametrisations. The TCN proposal outperforms the forecasting accuracy of Long Short-Term Memory (LSTM) recurrent networks, which are considered the state-of-the-art in the field. [ABSTRACT FROM AUTHOR]

The occurrence of outliers in real-world phenomena is quite usual. If these anomalous data are not properly treated, unreliable models can be generated. Many approaches in the literature are focused on a posteriori detection of outliers. However, a new methodology to a priori predict the occurrence of such data is proposed here. Thus, the main goal of this work is to predict the occurrence of outliers in time series, by using, for the first time, imbalanced classification techniques. In this sense, the problem of forecasting outlying data has been transformed into a binary classification problem, in which the positive class represents the occurrence of outliers. Given that the number of outliers is much lower than the number of common values, the resultant classification problem is imbalanced. To create training and test sets, robust statistical methods have been used to detect outliers in both sets. Once the outliers have been detected, the instances of the dataset are labeled accordingly. Namely, if any of the samples composing the next instance are detected as an outlier, the label is set to one. As a study case, the methodology has been tested on electricity demand time series in the Spanish electricity market, in which most of the outliers were properly forecast. [ABSTRACT FROM AUTHOR]

Climate change is increasing temperatures and causing periods of water scarcity in arid and semi-arid climates. The agricultural sector is one of the most affected by these changes, having to optimise scarce water resources. An important phenomenon within the water cycle is the evaporation from water reservoirs, which implies a considerable amount of water lost during warmer periods of the year. Indeed, evaporation rate forecasting can help farmers grow crops more sustainably by managing water resources more efficiently in the context of precision agriculture. In this work, we expose an interpretable machine learning approach, based on a multivariate decision tree, to forecast the evaporation rate on a daily basis using data from an Internet of Things (IoT) infrastructure, which is deployed on a real irrigated plot located in Murcia (southeastern Spain). The climate data collected feed the models that provide a forecast of evaporation and a summary of the parameters involved in this process. Finally, the results of the interpretable presented model are validated with the best literature models for evaporation rate prediction, i.e., Artificial Neural Networks, obtaining results very similar to those obtained for them, reaching up to 0.85 R 2 and 0.6 M A E . Therefore, in this work, a double objective is faced: to maintain the performance obtained by the models most frequently used in the problem while maintaining the interpretability of the knowledge captured in it, which allows better understanding the problem and carrying out appropriate actions. [ABSTRACT FROM AUTHOR]

A new methodology is presented for measuring, classifying and predicting the cycles of uncertainty that occur in temporary decision-making in the tourist accommodation market (apartments and hotels). Special attention is paid to the role of entropy and cycles in the process under the Adaptive Markets Hypothesis. The work scheme analyses random cycles from time to time, and in the frequency domain, the linear and nonlinear causality relationships between variables are studied. The period analysed is from January 2005 to December 2018; the following empirical results stand out: (1) On longer scales, the periodicity of the uncertainty of decision-making is between 6 and 12 months, respectively, for all the nationalities described. (2) The elasticity of demand for tourist apartments is approximately 1% due to changes in demand for tourist hotels. (3) The elasticity of the uncertainty factor is highly correlated with the country of origin of tourists visiting Spain. For example, it has been empirically shown that increases of 1% in uncertainty cause increases in the demand for apartments of 2.12% (worldwide), 3.05% (UK), 1.91% (Germany), 1.78% (France), 7.21% (Ireland), 3.61% (The Netherlands) respectively. This modelling has an explanatory capacity of 99% in all the models analysed. [ABSTRACT FROM AUTHOR]

Time series of mean monthly temperature and total monthly precipitation are two of the climatic variables most easily obtained from weather station records. There are many studies analyzing historical series of these variables, particularly in the Spanish territory. In this study, the series of these two variables in 47 stations of the provincial capitals of mainland Spain were analyzed. The series cover time periods from the 1940s to 2013; the studies reviewed in mainland Spain go up to 2008. ARIMA models were used to represent their variation. In the preliminary phase of description and identification of the model, a study to detect possible trends in the series was carried out in an isolated manner. Significant trends were found in 15 of the temperature series, and there were trends in precipitation in only five of them. The results obtained for the trends are discussed with reference to those of other, more detailed studies in the different regions, confirming whether the same trend was maintained over time. With the ARIMA models obtained, 12-month predictions were made by measuring errors with the observed data. More than 50% of the series of both were modeled. Predictions with these models could be useful in different aspects of seasonal job planning, such as wildfires, pests and diseases, and agricultural crops. [ABSTRACT FROM AUTHOR]

This work proposes a quantile regression neural network based on a novel constrained weighted quantile loss (CWQLoss) and its application to probabilistic short and medium-term electric-load forecasting of special interest for smart grids operations. The method allows any point forecast neural network based on a multivariate multi-output regression model to be expanded to become a quantile regression model. CWQLoss extends the pinball loss to more than one quantile by creating a weighted average for all predictions in the forecast window and across all quantiles. The pinball loss for each quantile is evaluated separately. The proposed method imposes additional constraints on the quantile values and their associated weights. It is shown that these restrictions are important to have a stable and efficient model. Quantile weights are learned end-to-end by gradient descent along with the network weights. The proposed model achieves two objectives: (a) produce probabilistic (quantile and interval) forecasts with an associated probability for the predicted target values. (b) generate point forecasts by adopting the forecast for the median (0.5 quantiles). We provide specific metrics for point and probabilistic forecasts to evaluate the results considering both objectives. A comprehensive comparison is performed between a selection of classic and advanced forecasting models with the proposed quantile forecasting model. We consider different scenarios for the duration of the forecast window (1 h, 1-day, 1-week, and 1-month), with the proposed model achieving the best results in almost all scenarios. Additionally, we show that the proposed method obtains the best results when an additive ensemble neural network is used as the base model. The experimental results are drawn from real loads of a medium-sized city in Spain. [ABSTRACT FROM AUTHOR]

This study aims to produce accurate predictions of the NO2 concentrations at a specific station of a monitoring network located in the Bay of Algeciras (Spain). Artificial neural networks (ANNs) and sequence-to-sequence long short-term memory networks (LSTMs) were used to create the forecasting models. Additionally, a new prediction method was proposed combining LSTMs using a rolling window scheme with a cross-validation procedure for time series (LSTM-CVT). Two different strategies were followed regarding the input variables: using NO2 from the station or employing NO2 and other pollutants data from any station of the network plus meteorological variables. The ANN and LSTM-CVT exogenous models used lagged datasets of different window sizes. Several feature ranking methods were used to select the top lagged variables and include them in the final exogenous datasets. Prediction horizons of t + 1, t + 4 and t + 8 were employed. The exogenous variables inclusion enhanced the model's performance, especially for t + 4 (ρ ≈ 0.68 to ρ ≈ 0.74) and t + 8 (ρ ≈ 0.59 to ρ ≈ 0.66). The proposed LSTM-CVT method delivered promising results as the best performing models per prediction horizon employed this new methodology. Additionally, per each parameter combination, it obtained lower error values than ANNs in 85% of the cases. [ABSTRACT FROM AUTHOR]

Forecasting future supply and demand is a topical subject in the olive oil sector due to its relevance for decision making and the lack of comprehensive and consensual estimates at the global level. This study aims at overcoming this gap in research by providing a foresight of global supply and demand for olive oil for the years to come. We use the Delphi technique to estimate the expected annual growth rates in the olive oil production and consumption worldwide as well as their likely impact on Spanish exports by 2025. Another key objective of the study is to elicit expert judgements on the factors that are likely to shape the predicted changes as well as the international challenges ahead. Results suggest substantial future increases in production in new-producing countries, in parallel with a slower growth in the European traditional suppliers whose focus will increasingly be placed on quality and sustainability rather than quantity. In addition, a significant growth in the world's demand for olive oil is expected in non-traditional markets, which will be driven by greater awareness of the positive health and sustainability attributes of this product, jointly with the changes in lifestyles and rising incomes of several consumer segments. These emerging markets offer promising prospects for the international expansion of olive oil companies. Future international challenges facing the olive oil industry include new market entry, worldwide product promotion, quality standards' harmonization, enacting trade facilitation schemes, and dealing with the COVID-19 impacts. Findings improve market predictability and transparency, and ultimately support decision-making and strategic planning in the olive oil sector. [ABSTRACT FROM AUTHOR]

In any electric power system, the Transmission System Operator (TSO) requires the use of short-term load forecasting algorithms. These predictions are essential for appropriate planning of the energy resources and optimal coordination for the generation agents. This study focuses on the development of a prediction model to be applied to the ten main Spanish islands: seven insular systems in the Canary Islands, and three systems in the Balearic Islands. An exhaustive analysis is presented concerning both the estimation results and the forecasting accuracy, benchmarked against an alternative prediction software and a set of modified models. The developed models are currently being used by the Spanish TSO (Red Eléctrica de España, REE) to make hourly one-day-ahead forecasts of the electricity demand of insular systems. [ABSTRACT FROM AUTHOR]

This work presents an analysis of low-visibility event persistence and prediction at Villanubla Airport (Valladolid, Spain), considering Runway Visual Range (RVR) time series in winter. The analysis covers long- and short-term persistence and prediction of the series, with different approaches. In the case of long-term analysis, a Detrended Fluctuation Analysis (DFA) approach is applied in order to estimate large-scale RVR time series similarities. The short-term persistence analysis of low-visibility events is evaluated by means of a Markov chain analysis of the binary time series associated with low-visibility events. We finally discuss an hourly short-term prediction of low-visibility events, using different approaches, some of them coming from the persistence analysis through Markov chain models, and others based on Machine Learning (ML) techniques. We show that a Mixture of Experts approach involving persistence-based methods and Machine Learning techniques provides the best results in this prediction problem. [ABSTRACT FROM AUTHOR]

The Holt–Winters models are one of the most popular forecasting algorithms. As well-known, these models are recursive and thus, an initialization value is needed to feed the model, being that a proper initialization of the Holt–Winters models is crucial for obtaining a good accuracy of the predictions. Moreover, the introduction of multiple seasonal Holt–Winters models requires a new development of methods for seed initialization and obtaining initial values. This work proposes new initialization methods based on the adaptation of the traditional methods developed for a single seasonality in order to include multiple seasonalities. Thus, new methods to initialize the level, trend, and seasonality in multiple seasonal Holt–Winters models are presented. These new methods are tested with an application for electricity demand in Spain and analyzed for their impact on the accuracy of forecasts. As a consequence of the analysis carried out, which initialization method to use for the level, trend, and seasonality in multiple seasonal Holt–Winters models with an additive and multiplicative trend is provided. [ABSTRACT FROM AUTHOR]

This project studies the conditions at which the maximum power point of a photovoltaic (PV) panel is obtained. It shows that the maximum power point is very sensitive to external disturbances such as temperature and irradiation. It introduces a novel method for maximizing the output power of a PV panel when connected to a DC/DC boost converter under variable load conditions. The main contribution of this work is to predict the optimum reference voltage of the PV panel at all-weather conditions using machine learning strategies and to use it as a reference for a Proportional-Integral-Derivative controller that ensures that the DC/DC boost converter provides a stable output voltage and maximum power under different weather conditions and loads. Evaluations of the proposed system, which uses an experimental photovoltaic dataset gathered from Spain, prove that it is robust against internal and external disturbances. They also show that the system performs better when using support vector machines as the machine learning strategy compared to the case when using general regression neural networks. [ABSTRACT FROM AUTHOR]