In the current competition framework governing the electricity sector, complex dependencies exist between electrical and market data, which complicates the decision-making procedure of energy actors. These must indeed operate within a complex, uncertain environment, and consequently need to rely on accurate multivariate, multi-step ahead probabilistic predictions. This paper aims to take advantage of recent breakthroughs in deep learning, while exploiting the structure of the problem to design prediction tools with tailored architectural alterations that improve their performance. The method can provide prediction intervals and densities, but is here extended with the objective to generate predictive scenarios. It is achieved by sampling the predicted multivariate distribution with a copula-based strategy so as to embody both temporal information and cross-variable dependencies. The effectiveness of the proposed methodology is emphasized and compared with several other architectures in terms of both statistical performance and impact on the quality of decisions optimized within a dedicated stochastic optimization tool of an electricity retailer participating in short-term electricity markets.

Energy storage systems (ESS) may provide the required flexibility to cost-effectively integrate weather-dependent renewable generation, in particular by offering operating reserves. However, since the real-time deployment of these services is uncertain, ensuring their availability requires merchant ESS to fully reserve the associated energy capacity in their day-ahead schedule. To improve such conservative policies, we propose a data-driven probabilistic characterization of the real-time balancing stage to inform the day-ahead scheduling problem of an ESS owner. This distributional information is used to enforce a tailored probabilistic guarantee on the availability of the scheduled reserve capacity via chance constrained programming, which allows a profit-maximizing participation in energy, reserve and balancing markets. The merit order-based competition with rival resources in reserve capacity and balancing markets is captured via a bi-level model, which is reformulated as a computationally efficient mixed-integer linear problem. Results show that a merchant ESS owner may leverage the competition effect to avoid violations of its energy capacity limits, and that the proposed risk-aware method allows sourcing more reserve capacity, and thus more value, from storage, without jeopardizing the real-time reliability of the power system.

The single imbalance pricing is an emerging mechanism in European electricity markets where all positive and negative imbalances are settled at a unique price. This real-time scheme thereby stimulates market participants to deviate from their schedule to restore the power system balance. However, exploiting this market opportunity is very risky due to the extreme volatility of the real-time power system conditions. In order to address this issue, we implement a new tailored deep-learning model, named encoder-decoder, to generate improved probabilistic forecasts of the imbalance signal, by efficiently capturing its complex spatio-temporal dynamics. The predicted distributions are then used to quantify and optimize the risk associated with the real-time participation of market players, acting as price-makers, in the imbalance settlement. This leads to an integrated forecast-driven strategy, modeled as a robust bilevel optimization. Results show that our probabilistic forecaster achieves better performance than other state of the art tools, and that the subsequent risk-aware robust dispatch tool allows finding a tradeoff between conservative and risk-seeking policies, leading to improved economic benefits. Moreover, we show that the model is computationally efficient and can thus be incorporated in the very-short-term dispatch of market players with flexible resources.

This paper presents a decision-making tool tailored for a portfolio manager aiming at maximizing its profit by participating in both energy and balancing services markets. The proposed formulation is modular and flexible so as to comply with any portfolio configuration and to follow evolutions of the market regulation policy. Detailed formulations of both medium-term (i.e., typically from one week up to one year-ahead) and short-term (i.e., day-ahead) perspectives are jointly considered and solved using surrogate-based optimization. The objective is to adequately account for the interdependencies and possible conflicting objectives between these time horizons. Then, in order to overcome the resulting computational burden associated with the different sources of uncertainty, an innovative method for generating time and space-dependent scenarios is developed. The approach is based on nonparametric copulas and, in contrast to traditional methods, allows including a large number of uncertain parameters into the formulation. Finally, the procedure is tested and illustrated for a portfolio manager with diversified assets. The case study is developed to emphasize the advantages of the proposed optimization tool in terms of accuracy and computational burden of the proposed models as well as subsequent generated profit.

Renewable Energy Communities consist in an emerging decentralized market mechanism which allows local energy exchanges between end-users, bypassing the traditional wholesale/retail market structure. In that configuration, local consumers and prosumers gather in communities and can either cooperate or compete towards a common objective, such as the minimization of the electricity costs and/or the minimization of greenhouse gas emissions for instance. This paper proposes data analytics modules which aim at helping the community members to schedule the usage of their resources (generation and consumption) in order to minimize their electricity bill. A day-ahead local wind power forecasting algorithm, which relies on state-of-the-art Machine Learning techniques currently used in worldwide forecasting contests, is in that way proposed. We develop furthermore an original method to improve the performance of neural network forecasting models in presence of abnormal wind power data. A technique for computing representative profiles of the community members electricity consumption is also presented. The proposed techniques are tested and deployed operationally on a pilot Renewable Energy Community established on an Medium Voltage network in Belgium, involving $2.25$$\mathrm{M}$$\mathrm{W}$ of wind and 18 Small and Medium Enterprises who had the possibility to freely access the results of the developed data modules by connecting to a dedicated web platform. We first show that our method for dealing with abnormal wind power data improves the forecasting accuracy by 10% in terms of Root Mean Square Error. The impact of the developed data modules on the consumption behaviour of the community members is then quantified, by analyzing the evolution of their monthly self-consumption and self-sufficiency during the pilot. No significant changes in the members behaviour, in relation with the information provided by the models, were observed in the recorded data. The pilot was however perturbed by the COVID-19 crisis which had a significant impact on the economic activity of the involved companies. We conclude by providing recommendations for the future set up of similar communities.

This paper addresses the voltage control problem in medium-voltage distribution networks. The objective is to cost-efficiently maintain the voltage profile within a safe range, in presence of uncertainties in both the future working conditions, as well as the physical parameters of the system. Indeed, the voltage profile depends not only on the fluctuating renewable-based power generation and load demand, but also on the physical parameters of the system components. In reality, the characteristics of loads, lines and transformers are subject to complex and dynamic dependencies, which are difficult to model. In such a context, the quality of the control strategy depends on the accuracy of the power flow representation, which requires to capture the non-linear behavior of the power network. Relying on the detailed analytical models (which are still subject to uncertainties) introduces a high computational power that does not comply with the real-time constraint of the voltage control task. To address this issue, while avoiding arbitrary modeling approximations, we leverage a deep reinforcement learning model to ensure an autonomous grid operational control. Outcomes show that the proposed model-free approach offers a promising alternative to find a compromise between calculation time, conservativeness and economic performance.