Search

• A cutting-edge technology is proposed for trade-off energy in buildings. • NSGA-II effectively optimizes the hyperparameters of the hybrid LSTM-MLP. • The use of NSGA-II reduces electricity costs and improves autarky levels. • The predictive methodology is able to manage several energy conditions in buildings. To conduct analysis on the field of electricity management in buildings is crucial to contribute to the clean energy promotion, energy efficiency, and resilience against climate change. This manuscript proposes a methodology for modeling a predictive and calibrated energy management system (EMS) using a hybrid methodology that combines long short-term memory and multilayer perceptron models (LSTM-MLP) optimized by non-dominated sorting genetic algorithm II (NSGA-II). The proposed approach utilizes global forecast system (GFS) data to anticipate energy consumption fluctuations and optimize the use of distributed energy sources, such as photovoltaic (PV) production, based on knowledge of the electricity prices in the free market one day ahead. This energy trade-off in the building is conducted with NSGA-II, guaranteeing the exploration and the exploitation of energy in the building while minimizing energy costs and energy wastes. The research carried out demonstrates the effectiveness of the hybrid LSTM-MLP model and the advantages of NSGA-II in hyperparameter tuning and in energy balance for sustainable building practices. The methodology conducted is tested in an existing building, the Industrial Engineering School located on the Campus Lagoas-Marcosende of the Universidade de Vigo, Spain. [ABSTRACT FROM AUTHOR]

Solar PV generation is renewable energy source that in the last years has contributed to reduce the use of fossil fuels. Controlling the efficiency of photovoltaic (PV) installations is essential in order for its use to spread. Deep learning (DL) models have demonstrated their efficiency in this context. The purpose of this work is to show a methodology to optimised deep learning models and show a specific application of the optimised model to characterise PV installations. The estimations yielded by this model are obtained without the need for real PV data to the training process; synthetic data are used. The built multivariate neural network is optimised through the use of a multiobjective genetic algorithm and the use of a feature engineering tool based on functional data analysis (FDA) clustering. This method was applied on synthetic data and on a PV installation located in north-western Spain, where the number of parallel modules, the azimuth and the slope in the installation are estimated. The results show that the model optimised using the non-dominant sorting genetic algorithm (NSGA-II) and the customised dataset with FDA, achieve lower errors or in the same range by reducing the complexity of the model or the complexity of the dataset used. Specifically, the bests models generates estimations with an average error between 6% and 18% on synthetic data and between 6% and 12% on real data. • An optimisation methodology is proposed to select the best LSTM architecture. • The optimisation is based on the multiobjective genetic algorithm NSGA-II. • A feature engineering tool based on FDA clustering is also proposed. • The models are evaluated based on the PV installations characterisation. • The results show the improvements provided by the optimisations presented. [ABSTRACT FROM AUTHOR]

Irrigation water demand is highly variable and depends on farmer behaviour, which affects the performance of irrigation networks. The irrigation depth applied to each farm also depends on farmer behaviour and is affected by precise and imprecise variables. In this work, a hybrid methodology combining artificial neural networks, fuzzy logic and genetic algorithms was developed to model farmer behaviour and forecast the daily irrigation depth used by each farmer. The models were tested in a real irrigation district located in southwest Spain. Three optimal models for the main crops in the irrigation district were obtained. The representability (R 2 ) and accuracy of the predictions (standard error prediction, SEP) were 0.72, 0.87 and 0.72; and 22.20%, 9.80% and 23.42%, for rice, maize and tomato crop models, respectively. [ABSTRACT FROM AUTHOR]

• Optimization of renewable energy communities considering environment and economy. • Combinatorial optimization for participant selection. • Multi-objective optimization of solar energy allocation. • Results show high avoided CO2 emissions and low paybacks for all participants. Renewable Energy Communities (REC) have the potential to become a key agent for the energy transition. Since consumers have different consumption patterns depending on their habits, their grouping allows for a better use of the resource. REC provide both economic and environmental benefits. However, its potential drastically diminishes when grouping of prosumers and energy al- location is performed improperly, as the energy generated ends up not being consumed. Given the importance of extracting the maximum potential of REC, this study presents a tool to assist in both the planning and the operation phases. We present a combinatorial optimization method for participant selection and a multi-objective (MO) optimization of solar energy allocation. Specific Ge- netic Algorithms (GA) were developed including problem-specific approaches for reducing the search space, encoding, techniques for space ordering, fitness functions, special operators to replace duplicate individuals and decoding for equality constraints. The performance of the novel solution approach was exper- imentally proved with an electrical solar installation and electricity consumers from Northern east Spain. The results show that the developed tool achieves energy sharing in REC with low solar energy excess, high self-consumption and high avoided CO2 emissions while assuring low payback periods for all partic- ipants. This tool will be essential to increase revenues of REC schemes and boost their beneficial environmental impact. [ABSTRACT FROM AUTHOR]

• Building stock modelling is implemented through a bottom-up method. • Dynamic simulations are applied through calibrated and parameterized stock models. • Optimal retrofit solutions under a 2050 future weather scenario are proposed. • Results are provided for four different climatic regions in southern Spain. • Results can be interactively accessed by stakeholders and the general public. Retrofitting the existing building stock is widely accepted as a crucial factor to reaching 2030 and 2050 climate and energy targets, given that the building sector is among the top three most dominant energy consumers. This paper presents a bottom-up study which uses calibrated and parameterized energy stock models (building archetypes), while also incorporating building stock information from a large database. The thermal performance of the existing social housing stock of southern Spain is assessed through dynamic simulation under present and future climate change scenarios. Subsequently, several passive and low-cost operation-related strategies are numerically optimized through genetic algorithms to determine the best retrofit solutions, taking into consideration global warming scenarios. A multi-objective decision analysis is carried out by optimizing annual overheating hours (%), annual undercooling hours (%), and investment costs (€/m2). Among the conclusions reported, it is important to note the feasibility of implementing low-cost retrofit strategies considering investment costs of up to around 200 €/m2, which would lead to average annual overheating and undercooling hours below 55 % and 45 %, respectively. However, retrofit solutions exclusively based on passive and low-cost operation measures were proven to be significantly limited to improve thermal comfort results in the social stock. [ABSTRACT FROM AUTHOR]

• A bottom-up approach is applied through calibrated parameterised stock energy models. • Information from a public database is incorporated into energy dynamic models. • Retrofit solutions are proposed optimising thermal comfort and investment costs. • Four Mediterranean climatic areas of southern Spain are assessed. • Interactive results can be easily accessed by stakeholders and the general public. There is an impending need to retrofit the existing social housing stock to improve thermal comfort and to reduce energy demand. This research proposes calibrated building stock models to assess thermal comfort of the social housing stock of southern Spain (Mediterranean area). Several retrofit strategies are optimised using a genetic algorithm to obtain the best retrofit solutions, considering three objectives: annual overheating hours (%), annual undercooling hours (%) and investment costs (€/m2). Results are shown for four different climatic areas in southern Spain. This study finds that it is possible to retrofit the aforementioned stock considering investment costs from approximately 20–200 €/m2. The percentage of improvements for each climatic area are as follows: in Sevilla (B4 climatic area), investments costs up to 50 €/m2 led to 40% and 20% annual overheating and undercooling hours. In Cádiz, (A3 climatic area), 15% and 22% overheating and undercooling hours were achieved with medium-cost solutions (50–100 €/m2). In Almería (A4 climatic area), also medium-cost strategies reported approximately 15% and 30% overheating and undercooling hours. In Granada (C3 climatic area), 15% and 38% overheating and undercooling hours were obtained with medium-cost measures. Yet, applying high-cost solutions (100–200 €/m2) only significantly improved thermal comfort in Almería and Sevilla. [ABSTRACT FROM AUTHOR]

Abstract: Solar thermal electricity technologies are attractive alternatives to produce electricity by means of a renewable source. One of these technologies is parabolic trough collectors. In Spain, the sale of solar electricity to the national grid is primed. There are three main parameters that affect the behaviour of these plants: area of solar collector field, capacity of thermal storage tanks and power of the auxiliary system. In this paper, a simplified model of the plant is used to optimize the size of its components that produces the maximum yearly profit. The use of traditional methods of optimization is not possible and genetic algorithms have been used. An important feature of the model is that the minimum level of the electricity production of the block of power can be fixed. Once the optimization has been performed, the traditional parameters that characterize the dimension of the plant are analysed (the solar multiple and the capacity factor). For a gross power of 50 MW, the optimum collector area varies between 583,000 m2 and 749,860 m2 with a thermal storage between 6.55 h and 13.46 h respectively. The economic benefit is always higher than 19.30 M€ per year and the cost of the electricity produced is about 18.5 c€/kWh. [Copyright &y& Elsevier]

Abstract: In previous works, many authors have widely used mass consistent models for wind field simulation by the finite element method. On one hand, we have developed a 3-D mass consistent model by using tetrahedral meshes which are simultaneously adapted to complex orography and to terrain roughness length. In addition, we have included a local refinement strategy around several measurement or control points, significant contours, as for example shorelines, or numerical solution singularities. On the other hand, we have developed a 2.5-D model for simulating the wind velocity in a 3-D domain in terms of the terrain elevation, the surface temperature and the meteorological wind, which is consider as an averaged wind on vertical boundaries. Using the meteorological wind as datum, the 2.5-D model provides a 3-D local wind modified by topography and thermal gradients on the surface by solving only a 2-D optimal control problem where the boundary condition is the control. In this case, the finite element discretization consists on a triangular mesh adapted to the terrain topography and roughness length. In both models, the wind field adjusts to several wind speed measurements at several points in the 3-D domain and eventually to an average wind flux on the boundary. In this paper we introduce several advances in the 2.5-D and 3-D wind models and we compare their results on a region located in the Province of Lugo (Spain) with realistic data that have been provided by the company Desarrollos Eólicos S.A. (DESA). In order to obtain the best adjustment of models results to the measurements, the main parameters governing the models are estimated by using genetic algorithms with a parallel implementation. [Copyright &y& Elsevier]

Abstract: This study explores the suitability of a soft computing technique to predict (forecast and hindcast) significant wave heights in some areas of the Mediterranean Sea. Using a 44-year database of meteorological and oceanographic records we train a genetic algorithm, to reconstruct a 44-year time series of significant wave height at different coastal points of the Balearic Islands (Western Mediterranean). The correlation obtained between the numerical model data and the algorithm output is . The equations obtained by the genetic algorithm are then used to predict significant wave heights measured at several buoys. We make use of the equation from the node closest to the buoy using as input wind data from the meteorological station at each buoy. We obtained that SWH at each buoy can be predicted with a 1-h ahead forecast time using only wind data from the previous 12h with a correlation of . [Copyright &y& Elsevier]

• Decision support system to help water utilities design practical work programs. • Two-stage grouping algorithm to aggregate water pipes into replacement programs. • Work programs optimization through a multi-objective genetic algorithm. • Integration of external criteria and the managers knowledge and experience. • Sensitivity analysis of the company's strategic policy on the work programs. Asset management in hydraulic infrastructures aims for the long-term sustainability of water distribution and wastewater networks. Strategic maintenance planning has thus been deeply analyzed in the literature for individual water and sewer pipes. However, water utilities do not plan and perform replacement activities on individual elements, but rather on coherent aggregations of neighboring pipes. We have developed a decision support system (DSS) to help water utilities design intervention programs for hydraulic infrastructures. It integrates a two-stage algorithm that groups water supply and sewer pipes into practical and efficient replacement works, based upon their proximity and their priority of renewal. A multi-objective genetic algorithm optimizes the work programs configurations while integrating the water company's strategic policy into an innovative multi-objective function. We have applied our methodology to a large water company in Spain and illustrated this application with a sensitivity analysis to determine how the company's strategic criteria influences the resulting work configurations. [ABSTRACT FROM AUTHOR]