A Machine Learning Model Ensemble for Mixed Power Load Forecasting across Multiple Time Horizons.

The increasing penetration of renewable energy sources tends to redirect the power systems community's interest from the traditional power grid model towards the smart grid framework. During this transition, load forecasting for various time horizons constitutes an essential electric utility task in network planning, operation, and management. This paper presents a novel mixed power-load forecasting scheme for multiple prediction horizons ranging from 15 min to 24 h ahead. The proposed approach makes use of a pool of models trained by several machine-learning methods with different characteristics, namely neural networks, linear regression, support vector regression, random forests, and sparse regression. The final prediction values are calculated using an online decision mechanism based on weighting the individual models according to their past performance. The proposed scheme is evaluated on real electrical load data sensed from a high voltage/medium voltage substation and is shown to be highly effective, as it results in R2 coefficient values ranging from 0.99 to 0.79 for prediction horizons ranging from 15 min to 24 h ahead, respectively. The method is compared to several state-of-the-art machine-learning approaches, as well as a different ensemble method, producing highly competitive results in terms of prediction accuracy.

Multi-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions.

The field of automatic collision avoidance for surface vessels has been an active field of research in recent years, aiming for the decision support of officers in conventional vessels, or for the creation of autonomous vessel controllers. In this paper, the multi-ship control problem is addressed using a model predictive controller (MPC) that makes use of obstacle ship trajectory prediction models built on the RBF framework and is trained on real AIS data sourced from an open-source database. The usage of such sophisticated trajectory prediction models enables the controller to correctly infer the existence of a collision risk and apply evasive control actions in a timely manner, thus accounting for the slow dynamics of a large vessel, such as container ships, and enhancing the cooperation between controlled vessels. The proposed method is evaluated on a real-life case from the Miami port area, and its generated trajectories are assessed in terms of safety, economy, and COLREG compliance by comparison with an identical MPC controller utilizing straight-line predictions for the obstacle vessel.

An Inverse Neural Controller Based on the Applicability Domain of RBF Network Models.

This paper presents a novel methodology of generic nature for controlling nonlinear systems, using inverse radial basis function neural network models, which may combine diverse data originating from various sources. The algorithm starts by applying the particle swarm optimization-based non-symmetric variant of the fuzzy means (PSO-NSFM) algorithm so that an approximation of the inverse system dynamics is obtained. PSO-NSFM offers models of high accuracy combined with small network structures. Next, the applicability domain concept is suitably tailored and embedded into the proposed control structure in order to ensure that extrapolation is avoided in the controller predictions. Finally, an error correction term, estimating the error produced by the unmodeled dynamics and/or unmeasured external disturbances, is included to the control scheme to increase robustness. The resulting controller guarantees bounded input-bounded state (BIBS) stability for the closed loop system when the open loop system is BIBS stable. The proposed methodology is evaluated on two different control problems, namely, the control of an experimental armature-controlled direct current (DC) motor and the stabilization of a highly nonlinear simulated inverted pendulum. For each one of these problems, appropriate case studies are tested, in which a conventional neural controller employing inverse models and a PID controller are also applied. The results reveal the ability of the proposed control scheme to handle and manipulate diverse data through a data fusion approach and illustrate the superiority of the method in terms of faster and less oscillatory responses.

Model predictive control for systems with fast dynamics using inverse neural models.

In this work, a novel model predictive control (MPC) scheme is introduced, by integrating direct and indirect neural control methodologies. The proposed approach makes use of a robust inverse radial basis function (RBF) model taking into account the applicability domain criterion, in order to provide a suitable initial starting point for the optimizer, thus helping to solve the optimization problem faster. The performance of the proposed controller is evaluated on the control of a highly nonlinear system with fast dynamics and compared with different control schemes. Results show that the proposed approach outperforms the rivaling schemes in terms of response; moreover, it solves the optimization problem in less than one sampling period, thus effectively rendering MPC-based controllers capable of handling systems with fast dynamics.

A Fast and Efficient Method for Training Categorical Radial Basis Function Networks.

This brief presents a novel learning scheme for categorical data based on radial basis function (RBF) networks. The proposed approach replaces the numerical vectors known as RBF centers with categorical tuple centers, and employs specially designed measures for calculating the distance between the center and the input tuples. Furthermore, a fast noniterative categorical clustering algorithm is proposed to accomplish the first stage of RBF training involving categorical center selection, whereas the weights are calculated through linear regression. The method is applied on 22 categorical data sets and compared with several different learning schemes, including neural networks, support vector machines, naïve Bayes classifier, and decision trees. Results show that the proposed method is very competitive, outperforming its rivals in terms of predictive capabilities in the majority of the tested cases.

A medical diagnostic tool based on radial basis function classifiers and evolutionary simulated annealing.

OBJECTIVE: The profusion of data accumulating in the form of medical records could be of great help for developing medical decision support systems. The objective of this paper is to present a methodology for designing data-driven medical diagnostic tools, based on neural network classifiers. METHODS: The proposed approach adopts the radial basis function (RBF) neural network architecture and the non-symmetric fuzzy means (NSFM) training algorithm, which presents certain advantages including better approximation capabilities and shorter computational times. The novelty in this work consists of adapting the NSFM algorithm to train RBF classifiers, and suitably tailoring the evolutionary simulated annealing (ESA) technique to optimize the produced RBF models. The integration of ESA is critical as it helps the optimization procedure to escape from local minima, which could arise from the application of the traditional simulated annealing algorithm, and thus discover improved solutions. The resulting method is evaluated in nine different medical benchmark datasets, where the common objective is to train a suitable classifier. The evaluation includes a comparison with two different schemes for training classifiers, including a standard RBF training technique and support vector machines (SVMs). Accuracy% and the Matthews Correlation Coefficient (MCC) are used for comparing the performance of the three classifiers. RESULTS: Results show that the use of ESA helps to greatly improve the performance of the NSFM algorithm and provide satisfactory classification accuracy. In almost all benchmark datasets, the best solution found by the ESA-NSFM algorithm outperforms the results produced by the SFM algorithm and SVMs, considering either the accuracy% or the MCC criterion. Furthermore, in the majority of datasets, the average solution of the ESA-NSFM population is statistically significantly higher in terms of accuracy% and MCC at the 95% confidence level, compared to the global optimum solution that its rivals could achieve. As far as computational times are concerned, the proposed approach was found to be faster compared to SVMs. CONCLUSIONS: The results of this study suggest that the ESA-NSFM algorithm can form the basis of a generic method for knowledge extraction from data originating from different kinds of medical records. Testing the proposed approach on a number of benchmark datasets, indicates that it provides increased diagnostic accuracy in comparison with two different classifier training methods.

Evolving RBF neural networks for adaptive soft-sensor design.

This work presents an adaptive framework for building soft-sensors based on radial basis function (RBF) neural network models. The adaptive fuzzy means algorithm is utilized in order to evolve an RBF network, which approximates the unknown system based on input-output data from it. The methodology gradually builds the RBF network model, based on two separate levels of adaptation: On the first level, the structure of the hidden layer is modified by adding or deleting RBF centers, while on the second level, the synaptic weights are adjusted with the recursive least squares with exponential forgetting algorithm. The proposed approach is tested on two different systems, namely a simulated nonlinear DC Motor and a real industrial reactor. The results show that the produced soft-sensors can be successfully applied to model the two nonlinear systems. A comparison with two different adaptive modeling techniques, namely a dynamic evolving neural-fuzzy inference system (DENFIS) and neural networks trained with online backpropagation, highlights the advantages of the proposed methodology.

Variable selection in nonlinear modeling based on RBF networks and evolutionary computation.

In this paper a novel variable selection method based on Radial Basis Function (RBF) neural networks and genetic algorithms is presented. The fuzzy means algorithm is utilized as the training method for the RBF networks, due to its inherent speed, the deterministic approach of selecting the hidden node centers and the fact that it involves only a single tuning parameter. The trade-off between the accuracy and parsimony of the produced model is handled by using Final Prediction Error criterion, based on the RBF training and validation errors, as a fitness function of the proposed genetic algorithm. The tuning parameter required by the fuzzy means algorithm is treated as a free variable by the genetic algorithm. The proposed method was tested in benchmark data sets stemming from the scientific communities of time-series prediction and medicinal chemistry and produced promising results.

A novel RBF neural network training methodology to predict toxicity to Vibrio fischeri.

This work introduces a neural network methodology for developing QSTR predictors of toxicity to Vibrio fischeri. The method adopts the Radial Basis Function (RBF) architecture and the fuzzy means training strategy, which is fast and repetitive, in contrast to most traditional training techniques. The data set that was utilized consisted of 39 organic compounds and their corresponding toxicity values to Vibrio fischeri, while lipophilicity, equalized electronegativity and one topological index were used to provide input information to the models. The performance and predictive ability of the RBF model were illustrated through external validation and various statistical tests. The proposed methodology can be used to successfully model toxicity to Vibrio fischeri for a heterogeneous set of compounds.

A new algorithm for online structure and parameter adaptation of RBF networks.

This paper deals with the problem of online adaptation of radial basis function (RBF) neural networks. A new adaptive training method is presented, which is able to modify both the structure of the network (the number of nodes in the hidden layer) and the output weights, as the algorithm proceeds. These adaptation capabilities make the algorithm suitable for modeling dynamical time varying systems, where not only the dynamics but also the operating region changes with time. Therefore, the important issue of extrapolation is faced successfully, but at the same time the algorithm takes care of the size of the network, by deleting the hidden node centers that remain inactive for a long time. The selection of the network centers is based on a fuzzy partition of the input space, which defines a number of fuzzy subspaces. The algorithm considers the centers of the fuzzy subspaces as candidates for becoming hidden node centers and makes the selections, so that at least one center is close enough to each input example. The proposed technique is illustrated through the application to time varying dynamical systems and is compared to other adaptive training methods.