Abstract
A hybrid population-based metaheuristic, Hybrid Canonical Differential Evolutionary Particle Swarm Optimization (hC-DEEPSO), is applied to solve Security Constrained Optimal Power Flow (SCOPF) problems. Despite the inherent difficulties of tackling these real-world problems, they must be solved several times a day taking into account operation and security conditions. A combination of the C-DEEPSO metaheuristic coupled with a multipoint search operator is proposed to better exploit the search space in the vicinity of the best solution found so far by the current population in the first stages of the search process. A simple diversity mechanism is also applied to avoid premature convergence and to escape from local optima. A experimental design is devised to fine-tune the parameters of the proposed algorithm for each instance of the SCOPF problem. The effectiveness of the proposed hC-DEEPSO is tested on the IEEE 57-bus, IEEE 118-bus and IEEE 300-bus standard systems. The numerical results obtained by hC-DEEPSO are compared with other evolutionary methods reported in the literature to prove the potential and capability of the proposed hC-DEEPSO for solving the SCOPF at acceptable economical and technical levels.

Abstract
The development of the smart grid concept implies major changes in the operation and planning of distribution systems, particularly in Low Voltage (LV) networks. The majority of small-scale Distributed Energy Resources (DER)-microgeneration units, energy storage devices, and flexible loads-are connected to LV networks, requiring local control solutions to mitigate technical problems resulting from its integration in the system. Simultaneously, LV connected DER can be aggregated in small cells in order to globally provide new functionalities to system operators. Within this view, the Microgrid (MG) concept has been pointed out as a solution to extend and decentralize the distribution network monitoring and control capability. An MG is a highly flexible, active, and controllable LV cell, incorporating microgeneration units based on Renewable Energy Sources (RES) or low carbon technologies for small-scale combined heat and power applications, energy storage devices, and loads. The coordination of MG local resources, achieved through an appropriated network of controllers and communication system, endows the LV system with sufficient autonomy to operate interconnected to the upstream network or autonomously-emergency operation. In this case, the potentialities of DER can be truly realized if the islanded operation is allowed and bottom-up black start functionalities are implemented. To achieve this operational capability, this chapter presents the control procedures to be used in such a system to deal with the islanded operation and to exploit the local generation resources as a way to help in power system restoration in case of an emergency situation. A sequence of actions for a black start procedure is identified, and it is expected to be an advantage for power system operation regarding reliability as a result from the presence of a huge amount of dispersed generation.

Abstract

Abstract
Falls are very rare and extremely difficult to acquire in free living conditions. Due to this, most of prior work on fall detection has focused on simulated datasets acquired in scenarios that mimic the real-world context, however, the validation of systems trained with simulated falls remains unclear. This work presents a transfer learning approach for combining a dataset of simulated falls and non-falls, obtained from young volunteers, with the real-world FARSEEING dataset, in order to train a set of supervised classifiers for discriminating between falls and non-falls events. The objective is to analyze if a combination of simulated and real falls could enrich the model. In the real-world, falls are a sporadic event, which results in imbalanced datasets. In this work, several methods for imbalance learning were employed: SMOTE, Balance Cascade and Ranking models. The Balance Cascade obtained less misclassifications in the validation set.There was an improvement when mixing the real falls and simulated non-falls compared to the case when only simulated falls were used for training. When testing with a mixed set with real falls and simulated non-falls, it is even more important to train with a mixed set. Moreover, it was possible to onclude that a model trained with simulated falls generalize better when tested with real falls, than the opposite. The overall accuracy obtained for the combination of different datasets were above 95 %. © 2018 IEEE.

Abstract
The economic impact of fraud is wide and fraud can be a critical problem when the prevention procedures are not robust. In this paper we create a model to detect fraudulent transactions, and then use a classification algorithm to assess if the agent is fraud prone or not. The model (BOND) is based on the analytics of an economic network of agents of three types: individuals, businesses and financial intermediaries. From the dataset of transactions, a sliding window of rows previously aggregated per agent has been used and machine learning (classification) algorithms have been applied. Results show that it is possible to predict the behavior of agents, based on previous transactions. © 2018, Springer International Publishing AG, part of Springer Nature.

Abstract
Demand response (DR) is one of the most cost-effective elements of residential and small industrial building for the purpose of reducing the cost of energy. Today with broadening of the smart grid, electricity market and especially smart home, using DR can reduce cost and even make profits for consumers. On the other hand, utilizing centralized controls and have bidirectional communications Bi-directional communication between DR aggregators and consumers make many problems such as scalability and privacy violation. In this chapter, we propose a multi-agent method based on a Q-learning algorithm Q-learning algorithm for decentralized control of DR. Q-learning is a model-free reinforcement learning Reinforcement learning technique and a simple way for agents to learn how to act optimally in controlled Markovian domains. With this method, each consumer adapts its bidding and buying strategy over time according to the market outcomes. We consider energy supply for consumers such as small-scale renewable energy generators. We compare the result of the proposed method with a centralized aggregator-based approach that shows the effectiveness of the proposed decentralized DR market Decentralized DR market. © Springer International Publishing AG, part of Springer Nature 2018.