The deployment of microgrids could be fostered by control systems that do not require very complex modelling, calibration, prediction and/or optimisation processes. This paper explores the application of Reinforcement Learning (RL) techniques for the operation of a microgrid. The implemented Deep Q-Network (DQN) can learn an optimal policy for the operation of the elements of an isolated microgrid, based on the interaction agent-environment when particular operation actions are taken in the microgrid components. In order to facilitate the scaling-up of this solution, the algorithm relies exclusively on historical data from past events, and therefore it does not require forecasts of the demand or the renewable generation. The objective is to minimise the cost of operating the microgrid, including the penalty of non-served power. This paper analyses the effect of considering different definitions for the state of the system by expanding the set of variables that define it. The obtained results are very satisfactory as it can be concluded by their comparison with the perfect-information optimal operation computed with a traditional optimisation model, and with a Naive model.

Non-intrusive load monitoring (NILM) has become an important subject of study, since it provides benefits to both consumers and utility companies. The analysis of smart meter signals is useful for identifying consumption patterns and user behaviors, in order to make predictions and optimizations to anticipate the use of electrical appliances at home. However, the problem with this kind of analysis rests in how to isolate individual appliances from an aggregated consumption signal. In this work, we propose an unsupervised disaggregation method based on a controlled dataset obtained using smart meters in a standard household. By using soft computing techniques, the proposed methodology can identify the behavior of each of the devices from aggregated consumption records. In the approach developed in this work, it is possible to detect changes in power levels and to build a box model, consisting of a sequence of rectangles of different heights (power) and widths (time), which is highly adaptable to the real-life working conditions of household appliances. The system was developed and tested using data collected at households in France and the UK (UK-domestic appliance-level electricity (DALE) dataset). The proposed analysis method serves as a basis to be applied to large amounts of data collected by distribution companies with smart meters.

Flexibility of distributed energy resources is increasingly needed in the electricity markets and grids. But this dispersed flexibility can be used efficiently only if it is aggregated to wholesale market products. A set of software tools was developed for an actor or a company who aggregates flexible household demand for the electricity market and network operators. The tools comprise 1) short term forecasting of electricity market prices, 2) forecasting loads and their responses to control signals, 3) optimal selection of the control signals and consequently also the responses in each situation, 4) relevant external interfaces, and 5) a database and coordinating logic that integrate the tools into toolbox software. In addition to the operational time horizon tools also tools were considered for longer term decision making such as support for development of a portfolio of retail and wholesale market contracts in order to manage risks and maximize the value of flexibility.

This paper studies an approach to identify representative operating and contingency (OC) scenarios for the design of underfrequency load-shedding (UFLS) schemes. In small isolated power systems, contingency scenarios are outages of generating units. Usually, only N-1 outages are considered. In this paper, simultaneous outages of several units are also taken into account. Data mining techniques such as K-Means and Fuzzy C-Means algorithms are used to group scenarios in terms of system frequency and to identify representative OC scenarios. The approach has been applied to the design of UFLS schemes of two of the Spanish isolated power systems. The results have also been compared to the common practice of scenario selection. Clustering techniques yielded to satisfactory results, i.e., representative OC scenarios can be identified. Furthermore, these representative OC scenarios cover a wider range of possible system responses than the scenarios selected following the common practice.