Abstract
The integration of renewable generation and electric vehicles (EVs) into smart grids poses an additional challenge to the stochastic energy resource management problem due to the uncertainty related to weather forecast and EVs user-behavior. Moreover, when electricity markets are considered, market price variations cannot be disregarded. In this paper, a two-stage stochastic programming approach to schedule the day-ahead operation of energy resources in smart grids under uncertainty is presented. A realistic case study is performed using a large-scale scenario with nearly 4 million variables with the goal to minimize expected operation cost of energy aggregators. Three scenarios are analyzed to understand the effect of market transactions and external suppliers on the aggregator model. The results suggest that the market transactions can reduce expected cost, while the external supplier offers risk-free price. In addition, the performance metric shows the superiority of the stochastic approach over an equivalent deterministic model. © 2018 Power Systems Computation Conference.

Abstract
This paper proposes an Artificial Neural Network (ANN) based approach to classify different contexts, with the goal of enhancing the management of residential energy resources. The increasing penetration of renewable based generation has completely changed the paradigm of the power and energy sector. The intermittent nature of these resources requires the system to incentivize the adaptability of consumers in order to guarantee the balance between generation and consumption. This leads to the emergence of several incentives with the objective of increasing the flexibility from the consumer's side. This, allied to the increasing price of electricity, leads to an increasing need for consumers to adapt their consumption in order to improve energy efficiency, decrease energy bills, and achieve a better use of their own generation resources. With this, several House Management Systems (HMS), and Building Energy Management Systems (BEMS) have emerged. These systems allow adapting the consumption (or suggesting changes in consumers' habits) according to several factors. However, in order to make this management truly smart, there is a need for adaptation to different contexts, so that changes can be done accordingly to the different situations that are faced at each time. This paper addresses this problem by proposing a novel methodology that enables classifying different situations in different contexts, according to different contextual variables. © 2017 IEEE.

Abstract

Abstract
The ability to predict future energy consumption is very important for energy distribution companies because it allows them to estimate energy needs and supply them accordingly. Consumption prediction makes it possible for those companies to optimize their processes by, for example, providing them with knowledge about future periods of high energy demand or by enabling them to adapt their tariffs to customer consumption. Machine Learning techniques allow to predict future energy consumption on the basis of the customers' historical consumption and several other parameters. This article reviews some of the main machine learning models capable of predicting energy consumption, in our case study we use a specific set of data extracted from a two-year-period of a shoe store. Among the evaluated methods, Gradient Boosting has obtained an 86.3% success rate in predicting consumption. © 2019 IEEE.

Abstract
The necessity of end-user engagement in power systems have become a reality in recent times. One of the solutions to this engagement is the creation of local energy markets. The distribution systems operators are compelled to investigate and optimize their asset investment cost in reinforcement of grids by introducing smart grid functionalities in order to avoid investments. The congestion management is the one of the most promising strategies to deal with the network issues. This paper presents a local electricity market or flexibility negotiation as a strategy in order to help the distribution system operator in congestion management. The local market is performed considering an asymmetric action model and is coordinated by an aggregator. A case study is presented considering a simulation that uses a low voltage network with 17 buses, which includes 9 consumers and 3 prosumers, all domestic users. Results show that using the proposed market model, the network congestion is avoided by taking advantage from the trading of consumers flexibility. © 2019 IEEE.

Abstract
The evolution of electricity markets towards local energy trading models, including peer-To-peer transactions, is bringing by multiple challenges for the involved players. In particular, small consumers, prosumers and generators, with no experience on participating in competitive energy markets, are not prepared for facing such an environment. This paper addresses this problem by proposing a decision support solution for small players negotiations in local transactions. The collaborative reinforcement learning concept is applied to combine different learning processes and reached an enhanced final decision for players actions in bilateral negotiations. The reinforcement learning process is based on the application of the Q-Learning algorithm; and the continuous combination of the different learning results applies and compares several collaborative learning algorithms, namely BEST-Q, Average (AVE)-Q; Particle Swarm Optimization (PSO)-Q, and Weighted Strategy Sharing (WSS)-Q and uses a model to aggregate these results. Results show that the collaborative learning process enables players' to correctly identify the negotiation strategy to apply in each moment, context and against each opponent. © 2019 IEEE.