Abstract

In this paper, the Multi-objective Genetic Algorithm (MOGA) is used to obtain the Pareto frontiers of conflicting objective functions for the fuzzy-Proportional-Integral-Derivative (fuzzy-PID) controllers. The ball–beam and inverted pendulum fourth order nonlinear systems are regarded as nonlinear benchmarks. The considered objective functions for the ball–beam system are the distance error of the ball, the angle error of the beam, and the control effort. For the inverted pendulum system, the objective functions are the distance error of the cart, the angle error of the pendulum, and the control effort, which must be minimized simultaneously. The Pareto fronts are compared with those obtained by Multi-objective Particle Swarm Optimization (MOPSO). Four points are chosen from nondominated solutions of the obtained Pareto fronts based on the three conflicting objective functions and used for illustration of the state variables of the controlled systems. Obtained results elucidate the efficiency of the proposed controller in order to control nonlinear systems.

Abstract

Proceedings of 7th International Symposium on Ambient Intelligence (ISAmI 2016), Seville, Spain on June 1st–3rd Stress is one of the most important factors in car accidents. When the driver is in this mental state, their skills and abilities are reduced. In this paper, we propose an algorithm to predict stress level on a road. Prediction model is based on deep learning. The stress level estimation considers the previous driver's driving behavior before reaching the road section, the road state (weather and traffic), and the previous driving made by the driver. We employ this algorithm to build a speed assistant. The solution provides an optimum average speed for each road stage that minimizes the stress. Validation experiment has been conducted using five different datasets with 100 samples. The proposal is able to predict the stress level given the average speed by 84.20% on average. The system reduces the heart rate (15.22%) and the aggressiveness of driving. The proposed solution is implemented on Android mobile devices and uses a heart rate chest strap. The research leading to these results has received funding from the “HERMES-SMART DRIVER/CITIZEN” projects TIN2013-46801-C4-2-R /1-R funded by the Spanish MINECO, from the grant PRX15/00036 from the Ministerio de Educación Cultura y Deporte. Document type: Part of book or chapter of book

Abstract

Mestrado em Engenharia Electrotécnica – Sistemas Eléctricos de Energia This thesis proposes a modified Particle Swarm Optimization (PSO) approach for the day-ahead scheduling of Distributed Energy Resources (DER) in smart grids, considering Electric Vehicles (EVs) with gridable capability (vehicle-to-grid). The proposed methodology introduces several changes in traditional PSO meta-heuristic to solve effectively the scheduling problem of DER with EVs. This thesis proposes an intelligent mechanism for adjusting the velocity limits of the swarm to alleviate violations of problem constraints and to improve the quality of the solution, namely the value of the objective function. In addition, a hybridization of PSO method is used, which combines this meta-heuristic with an exact method, a full ac power flow in order to validate network constraints of the solutions explored by the swarm. This thesis proposes a trip reduce demand response program for EVs users. A datamining based methodology is used to support the network operator in the definition of this program and to estimate how much demand response is adequate for a certain operation condition. The case studies included in the thesis aim to demonstrate the effectiveness of the modified PSO approach to the problem of DER scheduling considering EVs. An application named EV Scenario Simulator (EVeSSi) has been developed. EVeSSi allows creating scenarios considering EVs in distribution networks. A case study comparison of the modified PSO with an accurate mixed integer non-linear programming is presented. Furthermore, it is also compared with other variants of PSO, and the traditional PSO. Addionatly, different methods of EV battery management, namely uncontrolled charging, smart charging and vehicle-to-grid, are compared. Finally, a test case is presented to illustrate the use of the proposed demand response program for EVs and the data-mining methodology applied to a large database of operation scenarios. Esta tese apresenta uma aplicação modificada e adaptada da meta-heurística Particle Swarm Optimization (PSO) para o escalonamento de recursos energéticos em redes de distribuição inteligentes vulgo smart grids, considerando a utilização de veículos eléctricos. Este conceito em que os veiculos podem carregar e descarregar energia para a rede eléctrica é denominado na giria anglo-saxónica por vehicle-to-grid. Esta tese apresenta várias modificações na meta-heuristica PSO original para resolver mais eficazmente o problema do escalonamento de recursos energéticos com veículos eléctricos. Realça-se nesta tese a prosposta de um mecanismo inteligente para o ajustamento do limite das velocidades do swarm com vista a aliviar violações de restrições do problema e a melhorar a qualidade da solução, isto é, o valor da função objectivo. Adicionalmente, refere-se a hibridização desta meta-heurística com um método exacto, nomeadamente um trânsito de potências com o objectivo de verificar o cumprimento das restrições da rede eléctrica das soluções exploradas pelo swarm. Um programa de demand response para veículos eléctricos é apresentado na tese. Além disso, uma metodologia baseada em técnicas de data-mining é proposta para suportar as decisões do operator de sistema na definição e na estimativa do uso desse programa. Os casos de estudo incluídos nesta tese pretendem demonstrar a eficácia do PSO modificado no problema do escalonamento de recursos energéticos considerando os veículos eléctricos. Uma aplicação com a designação de EVeSSi foi desenvolvida e apresentada nesta tese para criar cenários de penetração de veículos eléctricos e simular os movimentos dos veículos ao longo dos nós das redes de distribuição. Um caso de estudo de comparação com um método exacto de programação não linear inteira mista é apresentado. Além disso, a aplicação proposta é comparada com outras variantes do PSO, incluindo a versão original. São ainda incluídos casos de estudo que abordam diferentes metodologias de interação do veículo com a rede, nomeadamente uncontrolled charging, smart charging e vehicle-to-grid. Por fim, é apresentado um caso de estudo com o programa de demand response e a metodologia de data-mining.

Abstract

http://www.icrat.org//icrat/Author/CharlieVanaret669/FINAL-329-cfp-Vanaret.pdf; International audience; Applying a benchmarking approach to conflict resolution problems is a hard task, as the analytical form of the constraints is not simple. This is especially the case when using realistic dynamics and models, considering accelerating aircraft that may follow flight paths that are not direct. Currently, there is a lack of common problems and data that would allow researchers to compare the performances of several conflict resolution algorithms. The present paper introduces a benchmarking approach that can provide researchers with common problems, in order to compare the performances of several conflict resolution algorithms. A comparison between three resolution methods is drawn over several problems and highlights assets and weaknesses for each of them.