Abstract Effective control of Energy Storage Systems (ESS) is crucial for the secure and profitable operation of microgrids. In this context, ESSs are essential for enhancing the overall grid resilience, balancing supply, and mitigating voltage and frequency variations. This paper presents a novel neuroevolutionary method, coupling a modified version of the Multi-Objective Evolutionary Policy Search (MEPS) algorithm with the Cross-Entropy method, aimed at optimizing an ESS control problem. The modified MEPS, named Cascade-MEPS, employs a cascade weights mutation operator to refine policies by focusing on the most recent hidden node, ensuring localized and non-disruptive adjustments. The resulting algorithm, referred to as cross-entropy Cascade-MEPS (CE-CMEPS), utilizes the cross-entropy method as a depth initialization strategy, conducting an initial exploration of the weights space to initialize the population prior to Cascade-MEPS execution. Experimental validation on a newly proposed multi-objective ESS control problem demonstrates the efficacy of CE-CMEPS, showcasing performance improvements and reduced variation compared to standalone MEPS. Our results show that CE-CMEPS is an effective ESS discharge controller and a sustainable multi-objective reinforcement learning solution.

Artificial Intelligence (AI) and Software Defined Radio (SDR) are transforming the field of signal intelligence. However, the full extent of the capabilities is unknown. This poster presents a paper in development that introduces a cloud-based platform leveraging artificial intelligence to detect and apply 11 modulation schemes (8 digital and 3 analog) to complex or quadrature radio signals. The SNR values analysed range from 0.0 to 40.0, with moderate drift, slight fading, and labelled increments. A comprehensive synthetic database developed by DeepSig is used to train four AI models. These will be integrated with the Google Cloud AI platform to enhance flexibility and processing power. The system will undergo testing with an SDR platform in GNU Radio, showcasing its potential for real-world signal processing applications. Cloud-based platforms offer the adaptability and computational power needed to replace traditional computers for AI-driven signal processing. Initial results indicate successful identification and accurate modulation type detection, with convenient access to the system through internet-connected devices.

ABSTRACT An accurate prediction of wind power generation is crucial for optimizing the integration of wind energy into the power grid, ensuring energy reliability. This research focuses on enhancing the accuracy of wind power generation forecasts by combining data from mesoscale and reanalysis models with Machine Learning (ML) approaches. We utilized WRF forecast data alongside ERA5 reanalysis data to estimate wind power generation for a wind farm located at Valladolid, Spain. The study evaluated the performance of ML models based on WRF and ERA5 data individually, as well as a combined model using inputs from both datasets. The hybrid model combining WRF and ERA5 data with ML resulted in a 15% improvement in root mean square error (RMSE) and a 10% increase in compared with standalone models, providing a more reliable 1‐h forecast of wind power generation. Additionally, the availability of data over time was addressed: WRF provides the advantage of projecting data into the future, whereas ERA5 offers retrospective data.

The surveillance multi-sensor placement is an important optimization problem that consists of positioning several sensors of different types to maximize the coverage of a determined area while minimizing the cost of the deployment. In this work, we tackle a modified version of the problem, consisting of spatially distributed multi-sensor placement for indoor surveillance. Our approach is focused on security surveillance of sensible indoor spaces, such as military installations, where distinct security levels can be considered. We propose an evolutionary algorithm to solve the problem, in which a novel special encoding (integer encoding with binary conversion) and effective initialization have been defined to improve the performance and convergence of the proposed algorithm. We also consider the probability of detection for each surveillance point, which depends on the distance to the sensor at hand, to better model real-life scenarios. We have tested the proposed evolutionary approach in different instances of the problem, varying both size and difficulty and obtained excellent results regarding the cost of sensors’ placement and convergence time of the algorithm. • Tackle a spatially distributed multi-sensors placement problem with security levels. • Useful for security surveillance of sensible indoor spaces, such as military installations. • Proposal of an evolutionary algorithm with specific encoding and effective initialization. • Comparison with alternative algorithms in different-sized scenarios.

Electricity demand prediction is crucial to ensure the operational safety and cost-efficient operation of the power system. Electricity demand has predominantly been predicted deterministically, while uncertainty analysis has been usually overlooked. To address this research gap, an integrated Neural Facebook Prophet (NFBP) model and Gaussian Kernel Density Estimation (KDE) model is proposed in this paper, as a way to obtain point and interval predictions of electricity demand, quantifying this way the uncertainty in the predictions. First, historical lagged data, created by utilizing the Partial Auto-correlation Function and Mutual Information Test, is applied to train a prediction model based on NFBP, Deep Learning (DL) as well as Statistical Models. Second, the model Prediction Errors (PE) are derived from the difference between actual and predicted values. A splitting strategy based on the mean and standard deviation of PE is proposed. Finally, electricity demand prediction intervals are obtained by applying Gaussian KDE on split PE. To verify the effectiveness of the proposed model, simulation studies are carried out for three prediction horizons on freely available datasets for the Bulimba sub-station in Southeast Queensland, Australia. Compared with DL models (Long-Short Term Memory Network and Deep Neural Network), the Root Mean Square Error of the NFBP model was reduced by 6.1% and 11.3% for 0.5-hr ahead, 22.7% and 26.3% for 6-hr ahead, and 31.8% and 29.9% for daily prediction. In addition, the Prediction Interval normalized Interval width is smaller in magnitude for the proposed NFBP-KDE model compared to other DL and Statistical models

Abstract Numerical association rule mining (NARM) is a popular method under the umbrella of data mining, focused on finding relationships between attributes in transaction databases. Numerical association rules for time series are a new paradigm that extends the applicability of NARM to the domain of time series. Association rule mining algorithms result in numerous rules, the interpretation of which is sometimes not easy for human experts. Therefore, various visualization methods have been developed to improve the explanation results of the rule mining process. This article is a novel contribution to the development of a new visualization method capable of presenting the association rules for time series developed according to the principles of explainable artificial intelligence. The experiments are conducted in the context of smart agriculture (i.e., agricultural time series data), and show the great potential of the proposed visualization method for the future.

Abstract This paper presents a novel implementation of the Coral Reef Optimization with Substrate Layers (CRO‐SL) algorithm. Our approach, which we call TensorCRO, takes advantage of the TensorFlow framework to represent CRO‐SL as a series of tensor operations, allowing it to run on GPU and search for solutions in a faster and more efficient way. We evaluate the performance of the proposed implementation across a wide range of benchmark functions commonly used in optimization research (such as the Rastrigin, Rosenbrock, Ackley, and Griewank functions), and we show that GPU execution leads to considerable speedups when compared to its CPU counterpart. Then, when comparing TensorCRO to other state‐of‐the‐art optimization algorithms (such as the Genetic Algorithm, Simulated Annealing, and Particle Swarm Optimization), the results show that TensorCRO can achieve better convergence rates and solutions than other algorithms within a fixed execution time, given that the fitness functions are also implemented on TensorFlow. Furthermore, we also evaluate the proposed approach in a real‐world problem of optimizing power production in wind farms by selecting the locations of turbines; in every evaluated scenario, TensorCRO outperformed the other meta‐heuristics and achieved solutions close to the best known in the literature. Overall, our implementation of the CRO‐SL algorithm in TensorFlow GPU provides a new, fast, and efficient approach to solving optimization problems, and we believe that the proposed implementation has significant potential to be applied in various domains, such as engineering, finance, and machine learning, where optimization is often used to solve complex problems. Furthermore, we propose that this implementation can be used to optimize models that cannot propagate an error gradient, which is an excellent choice for non‐gradient‐based optimizers.

In this paper the performance of different Machine Learning and Deep Learning approaches is evaluated in problems related to green mobility in big cities. Specifically, the forecasting of bike sharing demand in Madrid and Barcelona (Spain) is approached, for different prediction time-horizons, and also a problem of cable car demand forecasting in Madrid city. An important number of predictive variables are considered, which are grouped into four different sets (categorical/calendrical, persistence-based, meteorological and, as a novelty of the paper, information about analogue past instances), whose relevance is studied for all cases. A feature selection mechanism is also incorporated in order to improve the prediction accuracy of the proposed algorithms. A total of 12 different multivariate regression techniques are implemented, covering from Machine Learning methods to time-series Deep Learning approaches. Excellent results in all the prediction problems approached are reported. Finally, the consequences of obtaining accurate prediction in these three problem of green mobility in big cities are discussed. In addition, it is studied how the results could be exported to other similar cases in more general urban mobility studies. Novelties of the work include: (1) Addressing the forecast problem of passenger flow on a cable car using ML and DL multivariate techniques; (2) using the demand of analogous past instances as an additional feature to solve the demand prediction problems; and (3) the extraction of global conclusions about feature relevance when addressing a demand forecasting problem in green mobility.

This paper presents a method for providing explainability in the integration of artificial intelligence (AI) and data mining techniques when dealing with meteorological prediction. Explainable artificial intelligence (XAI) refers to the transparency of AI systems in providing explanations for their predictions and decision-making processes, and contribute to improve prediction accuracy and enhance trust in AI systems. The focus of this paper relies on the interpretability challenges in ordinal classification problems within weather forecasting. Ordinal classification involves predicting weather phenomena with ordered classes, such as temperature ranges, wind speed, precipitation levels, and others. To address this challenge, a novel and general explicable forecasting framework, that combines inductive rules and fuzzy logic, is proposed in this work. Inductive rules, derived from historical weather data, provide a logical and interpretable basis for forecasting; while fuzzy logic handles the uncertainty and imprecision in the weather data. The system predicts a set of probabilities that the incoming sample belongs to each considered class. Moreover, it allows the expert decision-making process to be strengthened by relying on the transparency and physical explainability of the model, and not only on the output of a black-box algorithm. The proposed framework is evaluated using two real-world weather databases related to wind speed and low-visibility events due to fog. The results are compared to both ML classifiers and specific methods for ordinal classification problems, achieving very competitive results in terms of ordinal performance metrics while offering a higher level of explainability and transparency compared to existing approaches.

In the context of reinforced concrete members subjected to shear, the steel behaviour, assumed as embedded in the concrete, has been modelled through different strategies. One of them, the so-called Refined Compression Field Theory (RCFT), is based on the concept of the concrete tension stiffening area, and shows a better fitting with the experimental results than other shear theories. However, for certain standard design conditions, the RCFT non-linear formulation does not throw a real physical solution for the steel yield strain, what hinders its numerical calculation. In fact, previous works have defined a solvability region for such strain. This non-linear equation is usually solved by iterative methods. However, the convergence of these methods depends on the root location. Moreover, their robustness may diminish in the boundary of the solvability region. This work validates Machine Learning (ML) approaches as alternative tools for the iterative prediction of the steel yield strain. To this aim, the calculation of the steel yield strain is performed in two stages, first locating the root to calculate using ML-based classification techniques, and second calculating such root with an accurate adjustment as a function of its location, using ML-based regression algorithms. As result, the efficiency of the proposed method no longer depends on the steel strain location. Finally, despite the high influence of the concrete bond parameter in the yield strain field, the ML prediction error is homogeneous over all the problem physical domain.

In this paper we propose and discuss different Deep Learning-based ensemble algorithms for a problem of low-visibility events prediction due to fog. Specifically, seven different Deep Learning (DL) architectures have been considered, from which multiple individual learners are generated. Hyperparameters of the models, including parameters concerning data preprocessing, models architecture and training procedure, are randomly selected for each model within a pre-defined discrete range. Also, every model is trained with slightly different data sampled randomly, assuring that every models introduce variety in the ensemble. Then, three different information fusion techniques are employed to build the ensemble models. The influence of the filtering process and the elitism level (the percentage of the individual models entering the ensemble) is also assessed. The performance of the proposed methodology have been tested in two real problems of low-visibility events prediction due to orographical and radiation fog, at the north of Spain. Comparison with different Machine Learning, alternative DL algorithms and meteorological-based methods show the good performance of the proposed deep learning ensembles in this problem.

Microgrids have become popular candidates for integrating diverse energy sources into the power grid as means of reducing fossil fuel usage. Energy Resource Management (ERM) is a type of Unit Commitment problem, where a player operates a microgrid with diverse renewable generators integrated with an external supplier. Calculating the economic dispatch of each committed unit on a planning horizon is an NP-hard problem, and therefore, finding an exact solution is difficult. This paper presents a multi-objective solution to the ERM problem from the perspective of battery operation and external supplier dispatch. First, a novel multi-objective decision problem modeling is proposed that considers three objectives: cost, greenhouse gas emissions, and battery degradation. This framework involves a learning agent that controls the depth of discharge of a Lithium-Ion battery. To address the proposed problem, a new multi-objective algorithm called Multi-Objective Evolutionary Policy Search (MEPS) is introduced. The proposed algorithm uses NeuroEvolution of Augmenting Topologies structure to evolve artificial neural networks for estimating action-preference values considering multi-objective rewards. The MEPS performance is evaluated on both standard and newly-proposed benchmark problems, using the hypervolume as the evaluation metric. When compared to standard deep reinforcement learning, results showed that MEPS provides cost-effective, environmentally friendly, and efficient energy storage management solutions. Furthermore, MEPS effectively solves the proposed ERM problem by finding neural networks with a small number of nodes and connections, which are suitable for use in embedded control systems. Overall, MEPS proved to be a promising multi-objective approach in the transition to clean energy resources.

Abstract Optimal power flow (OPF) is a complex, highly nonlinear, NP-hard optimization problem, in which the goal is to determine the optimal operational parameters of a power-related system (in many cases a type of smart or micro grid) which guarantee an economic and effective power dispatch. In recent years, a number of approaches based on metaheuristics algorithms have been proposed to solve OPF problems. In this paper, we propose the use of the Cross-Entropy (CE) method as a first step depth search operator to assist population-based evolutionary methods in the framework of an OPF problem. Specifically, a new variant of the Coral Reefs Optimization with Substrate Layers algorithm boosted with CE method (CE+CRO-SL) is presented in this work. We have adopted the IEEE 57-Bus System as a test scenario which, by default, has seven thermal generators for power production for the grid. We have modified this system by replacing three thermal generators with renewable source generators, in order to consider a smart grid approach with renewable energy production. The performance of CE+CRO-SL in this particular case study scenario has been compared with that of well-known techniques such as population’s methods CMA-ES and EPSO (both boosted with CE). The results obtained indicate that CE+CRO-SL showed a superior performance than the alternative techniques in terms of efficiency and accuracy. This is justified by its greater exploration capacity, since it has internally operations coming from different heuristics, thus surpassing the performance of classic methods. Moreover, in a projection analysis, the CE+CRO-SL provides a profit of millions of dollars per month in all cases tested considering the modified version of the IEEE 57-Bus smart grid system.

In this article, we propose a novel flexible architecture, with different algorithmic procedures, for effective story segmentation of broadcast news from subtitle files. The proposed system exploits spatial and temporal distance, as well as sentence similarity, to classify different stories in news broadcasts. The computational algorithms which form the architecture mainly focus on each sentence's features (temporal distance, spatial distance, and semantic similarity), and are combined to build an overall classifier. The first algorithm in the architecture focuses on the segmentation task, detecting boundaries between news. The second and third algorithms identify high semantic correlation between pieces of text, whether they are consecutive in space or not. Video Text Track (VTT) subtitle files are used to evaluate the performance of the proposed approach, although any file format that includes temporal information could also be considered. These VTT files may contain text errors and inaccuracies, and the proposed algorithms have been designed to deal with noisy content.

Optimal active–reactive power dispatch problems (OARPD) are considered large scale optimization problems with a high nonlinear complexity. Usually, in OARPD the objective is to minimize the cost of the system operation. In 2018, the IEEE PES committee proposed a competition, the “Operational planning of sustainable power systems”, in which a test bed relating the OARPD and a renewable energy generation challenge within a smart grid was proposed. In this work we consider three test scenarios proposed in that competition. Specifically, we present a hybrid meta-heuristic optimization approach applied to the OARPD, the Canonical Differential Evolutionary Particle Swarm Optimization (C-DEEPSO), to tackle these test scenarios. Comparative results with other algorithms such as CMA-ES, EPSO, and CEEPSO indicate that C-DEEPSO shows a competitive performance when solving the OARPD problems.

This study proposes a new hybrid deep learning (DL) model, the called CSVR, for Global Solar Radiation (GSR) predictions by integrating Convolutional Neural Network (CNN) with Support Vector Regression (SVR) approach. First, the CNN algorithm is used to extract local patterns as well as common features that occur recurrently in time series data at different intervals. Then, the SVR is subsequently adopted to replace the fully connected CNN layers to predict the daily GSR time series data at six solar farms in Queensland, Australia. To develop the hybrid CSVR model, we adopt the most pertinent meteorological variables from Global Climate Model and Scientific Information for Landowners database. From a pool of Global Climate Models variables and ground-based observations, the optimal features are selected through a metaheuristic Feature Selection algorithm, an Atom Search Optimization method. The hyperparameters of the proposed CSVR are optimized by mean of the HyperOpt method, and the overall performance of the objective algorithm is benchmarked against eight alternative DL methods, and some of the other Machine Learning approaches (LSTM, DBN, RBF, BRF, MARS, WKNNR, GPML and M5TREE) methods. The results obtained shows that the proposed CSVR model can offer several predictive advantages over the alternative DL models, as well as the conventional ML models. Specifically, we note that the CSVR model recorded a root mean square error/mean absolute error ranging between ≈ 2.172–3.305 MJ m2/1.624–2.370 MJ m2 over the six tested solar farms compared to ≈ 2.514–3.879 MJ m2/1.939–2.866 MJ m2 from alternative ML and DL algorithms. Consistent with this predicted error, the correlation between the measured and the predicted GSR, including the Willmott’s, Nash-Sutcliffe’s coefficient and Legates & McCabe’s Index was relatively higher for the proposed CSVR model compared to other DL and Machine Learning methods for all of the study sites. Accordingly, this study advocates the merits of CSVR model to provide a viable alternative to accurately predict GSR for renewable energy exploitation, energy demand or other forecasting-based applications.

This work proposes the design of both Single-Input–Single-Output (SISO) and Multiple-Input–Multiple-Output (MIMO) isolation controllers, when the interaction between the isolator system and the base structure is considered. The problem to be addressed is based on the reduction of the vibration of every platform, and also on the alignment between the different isolators. Both techniques, SISO and MIMO, are optimally tuned by the recently-proposed Coral Reefs Optimisation with Substrate Layers (CRO-SL), a multi-method ensemble evolutionary approach. In the proposed design, the stability of both systems (the isolators and the supporting structure) is verified. Also, the importance of considering the supporting structure dynamic is shown, by comparing the results with those obtained when the base structure is assumed to be rigid and infinitely heavy. This work shows considerable and not obvious improvements when the interaction between the isolator system and the base frame is considered. Numerical examples are included to illustrate the significant differences between using SISO and MIMO cases, and to motivate the use of CRO-SL. In addition, a real application example is analysed based on experimental data. Verified practical guidelines to be followed in experimental tests are finally shown.

In this work we present a pattern classification approach coupling the Neighbourhood Component Analysis (NCA) classifier with the Canonical Differential Evolutionary Particle Swarm Optimization (C-DEEPSO). The standard NCA uses the conjugate gradient method to minimize the classification error. Here we propose an approach using the C-DEEPSO instead. In the experimental design, the coupled approach is applied to 20 benchmark data sets, and its performance is compared with the standard NCA using the conjugate gradient. The experimental analysis shows the usage of an evolutionary approach to enhance the performance of a machine learning algorithm can be competitive when compared to well-known iterative optimization techniques, and even outperform them in some problems. A real-world problem classifying cyber-attacks to an industrial control system of gas pipelines is also solved by the proposed approach. The results obtained indicate the proposed approach can successfully identify possible cyber-attacks to the control system. In this way, the NCA coupled to C-DEEPSO can work as an Intrusion Detection Systems (IDS), being able to guarantee an acceptable security level.

The unit dispatch problem is defined as the attribution of operational values to each generation unit inside a hydro-power plant (HPP), given some criteria such as the total power to be generated, or the operational bounds of each unit. An optimal dispatch programming for hydroelectric units in HPP provides a larger production of electricity, with minimal water use. This paper presents an evolutionary approach to optimize the multi-criteria electric dispatch problem in a general HPP, based on a Multi-objective Evolutionary Swarm Hybridization (MESH) algorithm. The proposed approach integrates mathematical models and evolutionary swarm computation. The experimental analysis shows that the proposed MESH algorithm is able to reach competitive results when compared with classical evolutionary algorithms, the NGA-II and SPEA2 basing on ANOVA inference test. Results also show that the proposed MESH is able to save a large amount of water in the energy production process, supplying the requested load, and minimizing blackout risks and generating a profit around $275,000 monthly.

This paper tackles the short-term hydro-power unit commitment problem in a multi-reservoir system — a cascade-based operation scenario. For this, we propose a new mathematical modeling in which the goal is to maximize the total energy production of the hydro-power plant in a sub-daily operation, and, simultaneously, to maximize the total water content (volume) of reservoirs. For solving the problem, we discuss the Multi-objective Evolutionary Swarm Hybridization (MESH) algorithm, a recently proposed multi-objective swarm intelligence-based optimization method which has obtained very competitive results when compared to existing evolutionary algorithms in specific applications. The MESH approach has been applied to find the optimal water discharge and the power produced at the maximum reservoir volume for all possible combinations of turbines in a hydro-power plant. The performance of MESH has been compared with that of well-known evolutionary approaches such as NSGA-II, NSGA-III, SPEA2, and MOEA/D in a realistic problem considering data from a hydro-power energy system with two cascaded hydro-power plants in Brazil. Results indicate that MESH showed a superior performance than alternative multi-objective approaches in terms of efficiency and accuracy, providing a profit of $412,500 per month in a projection analysis carried out.

Energy is essential for all countries, since it is in the core of social and economic development. Since the industrial revolution, the demand for energy has increased exponentially. It is expected that the energy consumption in the world increases by 50% by 2030 [17]. As such, managing the demand of energy is of the uttermost importance. The development of tools to model and accurately predict the demand of energy is very important to policy makers. In this paper we propose the use of the Structured Grammatical Evolution (SGE) algorithm to evolve models of energy demand, over macro-economic indicators. The proposed SGE is hybridised with a Differential Evolution approach in order to obtain the parameters of the models evolved which better fit the real energy demand. We have tested the performance of the proposed approach in a problem of total energy demand estimation in Spain, where we show that the SGE is able to generate extremely accurate and robust models for the energy prediction within one year time-horizon.

Weather and atmospheric patterns are often persistent. The simplest weather forecasting method is the so-called persistence model, which assumes that the future state of a system will be similar (or equal) to the present state. Machine learning (ML) models are widely used in different weather forecasting applications, but they need to be compared to the persistence model to analyse whether they provide a competitive solution to the problem at hand. In this paper, we devise a new model for predicting low-visibility in airports using the concepts of mixture of experts. Visibility level is coded as two different ordered categorical variables: cloud height and runway visual height. The underlying system in this application is stagnant approximately in 90% of the cases, and standard ML models fail to improve on the performance of the persistence model. Because of this, instead of trying to simply beat the persistence model using ML, we use this persistence as a baseline and learn an ordinal neural network model that refines its results by focusing on learning weather fluctuations. The results show that the proposal outperforms persistence and other ordinal autoregressive models, especially for longer time horizon predictions and for the runway visual height variable.

The Community Detection Problem (CDP) in Social Networks has been widely studied from different areas such as Data Mining, Graph Theory Physics, or Social Network Analysis, among others. This problem tries to divide a graph into different groups of nodes (communities), according to the graph topology. A partition is a division of the graph where each node belongs to only one community. However, a common feature observed in real-world networks is the existence of overlapping communities, where a given node can belong to more than one community. This paper presents a new Multi-Objective Genetic Algorithm (MOGA-OCD) designed to detect overlapping communities, by using measures related to the network connectivity. For this purpose, the proposed algorithm uses a phenotype-type encoding based on the edge information, and a new fitness function focused on optimizing two classical objectives in CDP: the first one is used to maximize the internal connectivity of the communities, whereas the second one is used to minimize the external connections to the rest of the graph. To select the most appropriate metrics for these objectives, a comparative assessment of several connectivity metrics has been carried out using real-world networks. Finally, the algorithm has been evaluated against other well-known algorithms from the state of the art in CDP. The experimental results show that the proposed approach improves overall the accuracy and quality of alternative methods in CDP, showing its effectiveness as a new powerful algorithm for detecting structured overlapping communities.

Image registration (IR) is an extended and important problem in computer vision. It involves the transformation of different sets of image data having a shared content into a common coordinate system. Specifically, we will deal with the 3D intensity-based medical IR problem where the intensity distribution of the images is considered, one of the most complex and time consuming variants. The limitations of traditional IR methods have boomed the application of evolutionary and metaheuristic-based approaches to solve the problem, aiming to improve the performance of existing methods both in terms of accuracy and efficiency. In this contribution, we consider the use of a recently proposed bio-inspired meta-heuristic: the Coral Reef Optimization Algorithm (CRO). This novel algorithm simulates the natural phenomena underlying a coral reef, where different corals grow, reproduce and fight with other corals for space in the colony. CRO has recently obtained promising results in different real-world applications and we think its operation mode can properly cope with the 3D intensity-based medical IR problem. We adapt the algorithm to the real-coding problem nature and run an experimental setup tackling sixteen real-world problem instances. The new proposal is benchmarked with recent, state-of-the-art IR techniques. The results show that the CRO-based overcomes the state-of-the-art results in terms of its robustness and time efficiency.

This paper discuses the performance of two different Evolutionary Algorithms (EAs) in a problem of Optimal Placement of Distributed Power Generation (OPDPG) in Micro-Grids (MGs). Specifically, the problem consists of choosing the node/nodes to locate a number of different distributed generators with different technologies (such as micro wind turbines, photovoltaic panels, etc.), in such a way that the electrical power losses along a given time period (T) in the MG are minimized. We consider a situation where the network topology is already defined and where each node can have a load with different profiles allocated. The consumption profiles are real measurements of different types (residential, industrial, etc.) and will be hourly evaluated. The generations profiles are also real measurement data from different generation technologies. We consider two different encodings the EAs: first a binary-encoding approach, where each wind generator is represented by 2 bits and each solar generator by N bits, where N is the number of nodes that form the MG; and second, an integer-encoding approach, where both wind and PV generators are represented by 1 and 4 integer elements, respectively. Experiments are performed by considering three different MG topologies, with different number of nodes, in order to test the behavior of the algorithms with search spaces of increasing size. In these experimental scenarios we show how the binary approach attains better solutions than the integer-encoding approach, tough the computational time of the former is higher.

In this paper we propose an approach for feature selection in a problem of significant wave height prediction, to improve the exploitation of marine energy. The method that we present, a Grouping Genetic Algorithm — Extreme Learning Machine approach (GGA-ELM), mainly tries to improve the prediction performance of the regressors, providing more effective predictors and good performance in the final significant wave height prediction. In this method, the GGA looks for several subsets of features, and the ELM provides the fitness of the algorithm, through its accuracy on significant wave height prediction. The GGA is able to evolve different groups of features in parallel, which may improve the performance of the prediction obtained. After the feature selection process with the GGA-ELM, the final results are obtained by applying an ELM and also by a Support Vector Regressor algorithm, both working on the best GGA groups of features previously evolved. In the experimental part of the paper, we show the performance of the proposed approach in a real problem of significant wave height prediction at the West Coast of the USA, using variables directly obtained from several measuring buoys.

During the past years solar radiation prediction has become increasingly relevant among the scientific community and Machine Learning techniques have proven to be a useful tool to automatically learn an accurate prediction model. In this paper, we move one step further and try to gain interpretability during the learning process by introducing a novel feature selection approach. Our method trains a set of bootstrapped SVR classifiers to detect those features that are informative for the prediction task. This way we obtain a more robust set of selected features compared to other selection methods. This allows us to detect in a multivariate fashion not only the features needed to solve the prediction task, but also those that are informative for the problem at hand. The application of this algorithm to a Weather Research and Forecasting model, and its comparison to some state of the art tools, shows the advantages of the proposed method both in terms of resistance to overfitting, selection consistency and interpretability, while at the same time improving performance in terms of prediction accuracy.

This paper presents a new version of the Coral Reefs Optimization (CRO) algorithm to improve its performance in large scale global optimization problems. Specifically, we propose to extend the original CRO with different substrate layers, where several exploration operators are defined. This definition allows establishing a competitive co-evolution process within the CRO, which improves the search for optimal solution in large scale optimization problems. The new CRO with substrate layers (CRO-SL) is used in combination with a local search, and the final memetic algorithm obtained has been tested by using a test suite for large scale continuous optimization, showing a robust behavior.

In the so-called Big Data paradigm descriptive analytics are widely conceived as techniques and models aimed at discovering knowledge within unlabeled datasets (e.g. patterns, similarities, etc) of utmost help for subsequent predictive and prescriptive methods. One of these techniques is clustering, which hinges on different multi-dimensional measures of similarity between unsupervised data instances so as to blindly collect them in groups of clusters. Among the myriad of clustering approaches reported in the literature this manuscript focuses on those relying on bio-inspired meta-heuristics, which have been lately shown to outperform traditional clustering schemes in terms of convergence, adaptability and parallelization. Specifically this work presents a new clustering approach based on the processing fundamentals of the Ant Colony Optimization (ACO) algorithm, i.e. stigmergy via pheromone trails and progressive construction of solutions through a graph. The novelty of the proposed scheme beyond previous research on ACO-based clustering lies on a significantly pruned graph that not only minimizes the representation redundancy of the problem at hand, but also allows for an embedded estimation of the number of clusters within the data. However, this approach imposes a modified ant behavior so as to account for the optimality of entire paths rather than that of single steps within the graph. Simulation results over conventional datasets will evince the promising performance of our approach and motivate further research aimed at its applicability to real scenarios.

Summary The proliferation of social networks and their usage by a wide spectrum of user profiles has been specially notable in the last decade. A social network is frequently conceived as a strongly interlinked community of users, each featuring a compact neighborhood tightly and actively connected through different communication flows. This realm unleashes a rich substrate for a myriad of malicious activities aimed at unauthorizedly profiting from the user itself or from his/her social circle. This manuscript elaborates on a practical approach for the detection of identity theft in social networks, by which the credentials of a certain user are stolen and used without permission by the attacker for its own benefit. The proposed scheme detects identity thefts by exclusively analyzing connection time traces of the account being tested in a nonintrusive manner. The manuscript formulates the detection of this attack as a binary classification problem, which is tackled by means of a support vector classifier applied over features inferred from the original connection time traces of the user. Simulation results are discussed in depth toward elucidating the potentiality of the proposed system as the first step of a more involved impersonation detection framework, also relying on connectivity patterns and elements from language processing. Copyright © 2015 John Wiley & Sons, Ltd.

This paper proposes to tackle the structure design and operation of a Micro-Grid in a jointly way, by means of a novel nested Evolutionary Algorithms (EAs) approach. Specifically, in an scenario of variable electricity prices in an hourly basis, we apply different EAs, nested, to obtain optimal values for the sizing of generators and Energy Storage System (ESS), also to obtain the optimal values for each access tariff periods (structure part of the MG), and ESS scheduling (operational part of the MG). The proposed nested EAs starts from an initial solution for the ESS scheduling given by a deterministic approach (DA algorithm), from which an initial structure part is obtained by means of a first evolution. This part is set, and a different EA is then applied to obtain an improved ESS scheduling, which will be set to apply a different EA for the structure part. This scheme is applied in a sequential fashion for a number of evolutions. We will show that the proposed evolution scheme is able to obtain excellent results in terms of MG design, better than those by a single EA with the same number of function evaluations.

Solar irradiation prediction is an important problem in geosciences with direct applications in renewable energy. Recently, a high number of machine learning techniques have been introduced to tackle this problem, mostly based on neural networks and support vector machines. Gaussian process regression (GPR) is an alternative nonparametric method that provided excellent results in other biogeophysical parameter estimation. In this letter, we evaluate GPR for the estimation of solar irradiation. Noting the nonstationary temporal behavior of the signal, we develop a particular time-based composite covariance to account for the relevant seasonal signal variations. We use a unique meteorological data set acquired at a radiometric station that includes both measurements and radiosondes, as well as numerical weather prediction models. We show that the so-called temporal GPR outperforms ten state-of-the-art statistical regression algorithms (even when including time information) in terms of accuracy and bias, and it is more robust to the number of predictions used.

Network clustering is traditionally accomplished by relying just on the topology information, while a traffic-aware clustering approach has been recently proposed. The latter approach employs traffic matrices to take into account the intensity of the relationship between nodes. The extra effort needed to gather the traffic matrices is warranted if the composition of the clusters obtained in the traffic-based approach is significantly different from that obtained under the topology-based approach. In this paper we compare the outcomes of the two approaches, using the Rand Index as a similarity metric. For a variety of established clustering algorithms, and two large datasets, we show that the two approaches provide significantly different results, since the Rand Index lies far below one.

The selection of hyper-parameters in support vector machines for regression (SVMr) is an essential step in the training process of these learning machines. Unfortunately, there is not an exact method to obtain the optimal values of SVM hyper-parameters. Therefore, it is necessary to use a search algorithm in order to find the best set of hyper-parameters. Grid Search is the most commonly used option to perform such a hyper-parameters search, though other possibilities based on evolutionary computation algorithms have been proposed in the literature. In this paper we analyze the use of a standard genetic algorithm with binary encoding, which allows a fast exploration of the hyper-parameters space. We include a kind of tabu-list in the proposed algorithm, where we keep the last individuals generated by the genetic algorithm to avoid re-training of the SVMr with them. This technique allows a good improvement of the SVMr training time respect to the grid search approach, while keeping the machine accuracy almost unaltered.

This paper evaluates the performance of different classifiers when predicting wind speed from synoptic pressure patterns. The prediction problem has been formulated as a classification problem, where the different classes are associated to four values in an ordinal scale. The problem is relevant for long term wind speed prediction and also for wind speed reconstruction in areas (mainly wind farms) where there are not direct wind measures available. The results obtained in this paper present the Support Vector Machine as the best tested classifier for this task. In addition, the use of the intrinsic ordering information of the problem is shown to improve classifier performance.

This paper tackles the problem of sizing a standalone hybrid photovoltaic-batteries-hydrogen (PV-hydrogen) system, by applying an evolutionary algorithm. The system is specifically designed to cover the power necessities of remote, isolated telecommunications facilities, so it must be able to work in an unattended way during at least 2 years. Under this specific constraint, we develop an evolutionary algorithm which optimizes the number of PV panels and their distribution to feed two different arrays of batteries, and also the slope and azimuth of the panels. The well-known simulation program TRNSYS has been used in order to simulate the behavior of the real PV-hydrogen system. The evolutionary algorithm looks for the set of parameters which best performance of the system provide, in terms of hydrogen pressure remaining after two years and cost of the complete PV panels. The performance of the proposed evolutionary algorithm has been tested for the case of a real PV-hydrogen system sited at National Spanish Institute for Aerospace Technology (INTA), Torrejón de Ardoz, Madrid, Spain, where the proposed approach obtained a good solution which fulfils the constraint specifications of the system.

This paper presents a novel Grouping Harmony Search (GHS) algorithm for the Citywide Ubiquitous WiFi Network Design problem (WIFIDP). The WIFIDP is a NP-hard problem where private customers owning wireless access points connected to Internet share bandwidth with third parties. Aspects such as allocated budget and router capacities (coverage radius, capacity, price, etc) are taken into account in order to obtain the optimal network deployment (in terms of cost-effectiveness) when applying the GHS algorithm. The approach to tackle the aforementioned WIFIDP problem consists of a hybrid Grouping Harmony Search (GHS) algorithm with a local search method and a technique for repairing unfeasible solutions. Furthermore, the presented GHS algorithm is differential, since each proposed harmony is produced (improvised) based on the same harmony in the previous iteration. This differential scheme employs the grouping concept based on the connectivity between nomadic users and routers, which increases significantly its searching capability. Preliminary Monte Carlo simulations show that this proposed technique statistically outperforms genetically-inspired algorithms previously presented for the WIFIDP, with an emphasis in scenarios with stringent capacity and budget constraints. This first approach paves the way for future research aimed at applying the proposed algorithm to real scenarios.

While network clustering is traditionally accomplished just relying on the topology of the network, the new traffic-aware clustering approach employs traffic matrices to take into account the intensity of the relationship between nodes. In the context of traffic-aware clustering we propose a new Evolutionary Clustering algorithm and compare it with the Spectral Filtering algorithm. We compare them using both the Modularity and the Traffic-aware Scaled Coverage metrics, and two real-world datasets, each made of 1000 traffic matrices, respectively from Abilene and Géant networks. Our experiments show that Evolutionary Clustering performs better on all traffic matrices, excepting a minor number of traffic matrices in the Abilene network when the Modularity metric is employed.

Polyphase codes are widely used in radar systems as a pulse compression approach due to the fact that they produce lower side-lobes in the compressed signal than other methods. Unfortunately, the efficient design of such codes comprises by itself a non-linear n-dimensional NP-hard optimization problem, which has been so far tackled by using evolutionary techniques. In this paper we present a novel heuristic approach consisting of a Harmony Search algorithm hybridized with both a dynamic-step gradient-guided and a random walk local search procedures. The second procedure is applied when the gradient of the underlying fitness function is zero, i.e. when facing a flat region during the search process over the solution space. A simulation-based comparison study with the best results found in the literature is presented, from where it is concluded that our proposed algorithm outperforms other existing approaches in the literature for n=1,...,15.

A call center is a system used by companies to provide a number of services to customers, which may vary from providing simple information to gathering and dealing with complaints or more complex transactions. The design of this kind of system is an important task, since the trend is that companies and institutions choose call centers as the primary option for customer relationship management. This paper presents an evolutionary algorithm based on Dandelion encoding to obtain near-optimal service trees which represent the structure of the desired call center. We introduce several modifications to the original Dandelion encoding in order to adapt it to the specific problem of service tree design. Two search space size reduction procedures improve the performance of the algorithm. Systematic experiments have been tackled in order to show the performance of our approach: first, we tackle different synthetic instances, where we discuss and analyze several aspects of the proposed evolutionary algorithm, and second, we tackle a real application, the design of the call center of an Italian telecommunications company. In all the experiments carried out we compare our approach with a lower bound for the problem based on information theory, and also with the results of a Huffman algorithm we have used for reference.

In this paper we describe the application of a Hybrid Grouping Genetic Algorithm (HGGA) to the recent challenge of deploying metropolitan wireless networks, exploiting existing broadband infrastructure, by opening WiFi-enabled customers' DSL routers to third parties, or WiFi network Design Problem or WiFiDP. The application of a HGGA to this problem aims to produce the layout of a cost effective network deployment plan, considering real life aspects such as budget and DSL router characteristics (coverage, DSL capacity at a specific location, unit price, etc.) The total cost of deployment (i.e. the cost of opening all selected DSL routers for public use) should not exceed the allocated budget. The hybrid grouping genetic algorithm proposed includes a specific encoding to tackle the WiFiDP, in which the group part also includes the type of router to be installed. Moreover, a repairing and local search procedures are included in the algorithm to obtain better performance and always finding feasible solutions. The performance and effectiveness of the proposed HGGA is evaluated using two randomly generated WiFiDP instances (considering 1000 and 2000 users) that were used to perform several experiments. From theses datasets, we compare the results of the proposed HGGA with that of a greedy optimization algorithm previously proposed to solve the WiFiDP challenge.

A priority two-queue system, where high-priority customers receive a variable service rate is analyzed. The model can be used as a first approximated analysis for token-ring local-area networks where voice/data integration is accomplished. The voice service rate is variable according to the queue size at the instant the server reaches the voice queue. It is assumed that the larger the number of voice packets found by the server, the higher the voice service rate is. In contrast with other approaches, instead of dropping old voice packets, the proposed scheme can be considered to drop some amount of redundant information, transmitting only the remaining part, depending on the voice queue size. This strategy provides continuity of the voice service (at the price of reducing redundancy) in such a way that the loss of quality is distributed among several voice packets, which results in more regularity in the service.>

This paper proposes a neural network model for wind speed prediction, a very important task in wind parks management. Currently, several physical-statistical and artificial intelligence (AI) wind speed prediction models are used to this end. A recently proposed hybrid model is based on hybridizations of global and mesoscale forecasting systems, with a final downscaling step using a multilayer perceptron (MLP). In this paper, we test an alternative neural model for this final step of downscaling, in which projection hyperbolic tangent units (HTUs) are used within feed forward neural networks. The architecture, weights and node typology of the HTU-based network are learnt using a hybrid evolutionary programming algorithm. This new methodology is tested over a real problem of wind speed forecasting, in which we show that our method is able to improve the performance of previous MLPs, obtaining an interpretable model of final regression for each turbine in the wind park.

In this paper we present an application of the grouping genetic algorithm to the problem of assigning students to laboratory groups in university courses. This problem includes an important constraint of capacity, due to laboratories usually have a maximum number of equips or computers available, so the number of total students in a group is constrained to be equal or less than the capacity of the laboratory. In addition, our approach considers the case in which the students provide a sorted list of preferred laboratory groups, so the objective of the assignment must take this point into account. Another case in which lecturers' preferences are considered is also treated. The performance of the approach is shown in several test instances of the problem and compared with the results of an existing heuristic algorithm.

Call centers represent now an important channel for customer care activities. Most services provided by call centers are now accomplished in automated way to save operational costs. The customer is guided through a menu of options, which can be represented as a service tree, down to the desired service. In order to meet QoS constraints the service tree must be designed to minimize the average service time. An optimization algorithm, based on the combined use of Dandelion encoding and evolutionary operators, is proposed here to design the service trees with minimum average service time. The proposed algorithm provides trees whose average service time is lower than that obtained by the reference Huffman coding and is typically within 2% of the absolute lower bound represented by the entropic bound.

This paper presents the hybridization of global and mesoscale weather forecasting models with neural networks in order to tackle a problem of short-term wind speed prediction. The mean hourly wind speed forecast at aero-generators in a wind park is an important parameter used to predict the total energy production of the park. Our model for short-term wind speed forecast integrates two different meteorological prediction global models, observations at surface level and in different heights using atmospheric soundings. Also, it includes a mesoscale prediction model and a neural network to obtain the wind speed forecast in an specific point of the wind park. In the experiments carried out, we present some results of wind speed forecast in two aero-generators in a wind park at the south east of Spain. The results are encouraging, and show that our hybrid weather forecast models-neural network approach is able to obtain good short-term predictions of wind speed at specific points.

]This paper presents a hybrid genetic algorithm for solving a logic-type puzzle known as lights-up puzzle. The algorithm uses a binary Hopfield neural network to solve part of the puzzle constraint as it looks for good quality solution in term of the puzzle’s objective function. We show the good performance of our approach in a number of lights up puzzles instances downloaded from the internet.

This paper presents a hybrid evolutionary programming algorithm to solve the spread spectrum radar polyphase code design problem. The proposed algorithm uses an Evolutionary Programming (EP) approach as global search heuristic. This EP is hybridized with a gradient-based local search procedure which includes a dynamic step adaptation procedure to perform accurate and efficient local search for better solutions. Numerical examples demonstrate that the algorithm outperforms existing approaches for this problem.

We present an evolutionary approach to speaker segmentation, an activity that is especially important prior to speaker recognition and audio content analysis tasks. Our approach consists of a genetic algorithm (GA), which encodes possible segmentations of an audio record, and a measure of mutual information between the audio data and possible segmentations, which is used as fitness function for the GA. We introduce a compact encoding of the problem into the GA which reduces the length of the GA individuals and improves the GA convergence properties. Our algorithm has been tested on the segmentation of real audio data, and its performance has been compared with several existing algorithms for speaker segmentation, obtaining very good results in all test problems.

The widespread deployment of WDM optical networks posts lots of new challenges for network designers. Traffic grooming is one of the most common problems. Efficient grooming of traffic can effectively reduce the overall cost of the network. But unfortunately, traffic grooming problems have been shown to be NP-hard. Therefore, new heuristics must be devised to tackle them. Among these approaches, metaheuristics are among the most promising ones. In this paper, we present a thorough and comprehensive survey on various metaheuristic approaches to the grooming of traffic in both static and dynamic patterns in WDM optical networks. Some future challenges and research directions are also discussed in this paper.

Terminal assignment (TA) is important in increasing the telecommunication networks' capacity and reducing the cost of it. We propose a tabu search (TS) approach to solve the problem with non-standard cost functions. A greedy decoding approach is used to generate the initial solution and then an effective and unique search approach is proposed to produce the neighborhood, which exchange one of the terminals in each concentrator to improve the quality of solution. Simulation results with the proposed TS approach are compared with those using genetic and greedy algorithms. Computer simulations show that our approach achieves very good results in solving this problem.

In this paper, a twofold approach to improve the performance of genetic algorithms (GAs) in the feature selection problem (FSP) is presented. First, a novel genetic operator is introduced to solve the FSP. This operator fixes in each iteration the number of features to be selected among the available ones and consequently reduces the size of the search space. This approach yields two main advantages: a) training the learning machine becomes faster and b) a higher performance is achieved by using the selected subset. Second, we propose using the Walsh expansion of the FSP fitness function in order to perform ranking on the problem features. Ranking features have been traditionally considered to be a challenging problem, especially significant in health sciences where the number of available and potentially noisy signals is high. Three real biological datasets are used to test the behavior of the two approaches proposed.

A hybrid Hopfield network-simulated annealing algorithm (HopSA) is presented for the frequency assignment problem (FAP) in satellite communications. The goal of this NP-complete problem is minimizing the cochannel interference between satellite communication systems by rearranging the frequency assignment, for the systems can accommodate the increasing demands. The HopSA algorithm consists of a fast digital Hopfield neural network which manages the problem constraints hybridized with a simulated annealing which improves the quality of the solutions obtained. We analyze the problem and its formulation, describing and discussing the HopSA algorithm and solving a set of benchmark problems. The results obtained are compared with other existing approaches in order to show the performance of the HopSA approach.

This paper presents a hybrid Hopfield network-genetic algorithm (GA) approach to tackle the terminal assignment (TA) problem. TA involves determining minimum cost links to form a communications network, by connecting a given set of terminals to a given collection of concentrators. Some previous approaches provide very good results if the cost associated with assigning a single terminal to a given concentrator is known. However, there are situations in which the cost of a single assignment is not known in advance, and only the cost associated with feasible solutions can be calculated. In these situations, previous algorithms for TA based on greedy heuristics are no longer valid, or fail to get feasible solutions. Our approach involves a Hopfield neural network (HNN) which manages the problem's constraints, whereas a GA searches for high quality solutions with the minimum possible cost. We show that our algorithm is able to achieve feasible solutions to the TA in instances where the cost of a single assignment in not known in advance, improving the results obtained by previous approaches. We also show the applicability of our approach to other problems related to the TA.

The broadcast scheduling problem (BSP) arises in frame design for packet radio networks (PRNs). The frame structure determines the main communication parameters: communication delay and throughput. The BSP is a combinatorial optimization problem which is known to be NP-hard. To solve it, we propose an algorithm with two main steps which naturally arise from the problem structure: the first one tackles the hardest contraints and the second one carries out the throughput optimization. This algorithm combines a Hopfield neural network for the constraints satisfaction and a genetic algorithm for achieving a maximal throughput. The algorithm performance is compared with that of existing algorithms in several benchmark cases; in all of them, our algorithm finds the optimum frame length and outperforms previous algorithms in the resulting throughput.