arXiv subjects

Jonathan Dumas

Publications and source records attributed to Jonathan Dumas.

16 recordsLinked to original sources

arXiv2025

Analysis of the French system imbalance paving the way for a novel operating reserve sizing approach

This paper examines the relationship between system imbalance and several explanatory variables within the French electricity system. The factors considered include lagged imbalance values, observations of renewable energy sources (RES) generation and consumption, and forecasts for RES generation and consumption. The study analyzes the distribution of system imbalance in relation to these variables. Additionally, an HGBR machine-learning model is employed to assess the predictability of imbalances and the explanatory power of the input variables studied. The results indicate no clear correlation between RES generation or consumption and the observed imbalances. However, it is possible to predict the imbalance adequately using forecasts available a few hours before real-time, along with the lagged values of the imbalance. Predicting the imbalance a day in advance proves to be complex with the variables examined; however, the extreme quantiles of the imbalance used for reserve sizing and contracting can be predicted with sufficient accuracy.

eess.SY↗

arXiv2023

Stochastic optimization for unit commitment applied to the security of supply: extended version

Transmission system operators employ reserves to deal with unexpected variations of demand and generation to guarantee the security of supply. The French transmission system operator RTE dynamically sizes the required margins using a probabilistic approach relying on continuous forecasts of the main drivers of the uncertainties of the system imbalance and a 1 % risk threshold. However, this criterion does not specify which means to activate upward/downward and when to face a deficit of available margins versus the required margins. Thus, this work presents a strategy using a probabilistic unit commitment with a stochastic optimization-based approach, including the fixed and variable costs of units and the costs of lost load and production. The abstract problem is formulated with a multi-stage stochastic program and approximated with a heuristic called two-stage stochastic model predictive control. It solves a sequence of two-stage stochastic programs to conduct the central dispatch. An implementation is conducted by solving an approximated version with a single two-stage stochastic program. This method is tested on a real case study comprising nuclear and fossil-based units with French electrical consumption and renewable production.

math.OC↗

arXiv2023

Deep Generative Methods for Producing Forecast Trajectories in Power Systems

With the expansion of renewables in the electricity mix, power grid variability will increase, hence a need to robustify the system to guarantee its security. Therefore, Transport System Operators (TSOs) must conduct analyses to simulate the future functioning of power systems. Then, these simulations are used as inputs in decision-making processes. In this context, we investigate using deep learning models to generate energy production and load forecast trajectories. To capture the spatiotemporal correlations in these multivariate time series, we adapt autoregressive networks and normalizing flows, demonstrating their effectiveness against the current copula-based statistical approach. We conduct extensive experiments on the French TSO RTE wind forecast data and compare the different models with \textit{ad hoc} evaluation metrics for time series generation.

cs.LG↗

arXiv2023

Dynamic sizing of required balancing capacities: the operational approach in France

System operators employ operating reserves to deal with unexpected variations of demand and generation and guarantee the security of supply. However, they face new challenges to ensure this mission with the increasing share of renewable generation. This article focuses on the operational approach adopted by the French transmission system operator RTE for dynamically sizing the required margins in the dynamic margin monitoring strategy context. It relies on continuous forecasts of the main drivers of the uncertainties of the system imbalance. Four types of forecast errors, assumed to be independent, are considered in this approach: the errors in the wind and photovoltaic power generation, production of conventional power units, and electricity consumption. Then, the required margin is the result of comparing the global forecast error, computed as the convolution of these independent errors, with a security of supply criterion. This study presents the results of this method implemented at RTE and used in real-time operation.

eess.SY↗

arXiv2023

Multi-objective near-optimal necessary conditions for multi-sectoral planning

This paper extends the concepts of epsilon-optimal spaces and necessary conditions for near-optimality from single-objective to multi-objective optimisation. These notions are first presented for single-objective optimisation, and the mathematical formulation is adapted to address the multi-objective framework. Afterwards, we illustrate the newly developed methodology by conducting multi-sectoral planning of the Belgian energy system with an open-source model called EnergyScope TD. The cost and energy invested in the system are used as objectives. Optimal and efficient solutions for these two objectives are computed and analysed. These results are then used to obtain necessary conditions corresponding to the minimum amount of energy from different sets of resources, including endogenous and exogenous resources. This case study highlights the high dependence of Belgium on imported energy while demonstrating that no individual resource is essential on its own.

math.OC↗

arXiv2022

Denoising diffusion probabilistic models for probabilistic energy forecasting

Scenario-based probabilistic forecasts have become vital for decision-makers in handling intermittent renewable energies. This paper presents a recent promising deep learning generative approach called denoising diffusion probabilistic models. It is a class of latent variable models which have recently demonstrated impressive results in the computer vision community. However, to our knowledge, there has yet to be a demonstration that they can generate high-quality samples of load, PV, or wind power time series, crucial elements to face the new challenges in power systems applications. Thus, we propose the first implementation of this model for energy forecasting using the open data of the Global Energy Forecasting Competition 2014. The results demonstrate this approach is competitive with other state-of-the-art deep learning generative models, including generative adversarial networks, variational autoencoders, and normalizing flows.

cs.LG↗

arXiv2022

The energy return on investment of whole energy systems: application to Belgium

Planning the defossilization of energy systems by facilitating high penetration of renewables and maintaining access to abundant and affordable primary energy resources is a nontrivial multi-objective problem. However, so far, most long-term policies to decrease the carbon footprint of our societies consider the cost of the system as the leading indicator in the energy system models. This paper is the first to develop a novel approach by adding the energy return on investment (EROI) to a whole energy system optimization model. We built the database with all EROI technologies and resources considered. In addition, moving away from fossil-based to carbon-neutral energy systems raises the issue of the uncertainty of low-carbon technologies and resource data. Thus, we conducted a global sensitivity analysis to identify the main parameters driving the variations in the EROI of the system. This novel approach can be applied to any energy system, and we use a real-world case study to illustrate the model: the 2035 Belgian energy system for several greenhouse gas emissions targets. The main results are threefold: (i) the EROI of the system decreases from 8.9 to 3.9 when greenhouse gas emissions are reduced by 5; (ii) the renewable fuels - mainly imported renewable gas - represent the largest share of the system primary energy mix; (iii) in the sensitivity analysis, the renewable fuels drive 67% of the variation of the EROI of the system for low greenhouse gas emissions scenarios. The decrease in the EROI raises questions about meeting the climate targets without adverse socio-economic impact. Most countries rely massively on fossil fuels, and they could encounter an EROI decline when shifting to carbon neutrality. Thus, this study demonstrates the importance of considering other criteria, such as EROI, in energy system models.

eess.SY↗

arXiv2021

Microgrid management with weather-based forecasting of energy generation, consumption and prices

The Intergovernmental Panel on Climate Change proposes different mitigation strategies to achieve the net emissions reductions that would be required to follow a pathway that limits global warming to 1.5°C with no or limited overshoot. The transition towards a carbon-free society goes through an inevitable increase in the share of renewable generation in the energy mix and a drastic decrease in the total consumption of fossil fuels. Therefore, this thesis studies the integration of renewables in power systems by investigating forecasting and decision-making tools. Indeed, in contrast to conventional power plants, renewable energy is subject to uncertainty. Most of the generation technologies based on renewable sources are non-dispatchable, and their production is stochastic and complex to predict in advance. A high share of renewables is challenging for power systems that have been designed and sized for dispatchable units. In this context, probabilistic forecasts, which aim at modeling the distribution of all possible future realizations, have become a vital tool to equip decision-makers, hopefully leading to better decisions in energy applications. This thesis focuses on two main research questions: (1) How to produce reliable probabilistic renewable generation forecasts, consumption, and electricity prices? (2) How to make decisions with uncertainty using probabilistic forecasts? The thesis perimeter is the energy management of "small" systems such as microgrids at a residential scale on a day-ahead basis. It is divided into two main parts to propose directions to address both research questions (1) a forecasting part; (2) a planning and control part.

eess.SY↗

arXiv2021

A Probabilistic Forecast-Driven Strategy for a Risk-Aware Participation in the Capacity Firming Market: extended version

This paper addresses the energy management of a grid-connected renewable generation plant coupled with a battery energy storage device in the capacity firming market, designed to promote renewable power generation facilities in small non-interconnected grids. The core contribution is to propose a probabilistic forecast-driven strategy, modeled as a min-max-min robust optimization problem with recourse. It is solved using a Benders-dual cutting plane algorithm and a column and constraints generation algorithm in a tractable manner. A dynamic risk-averse parameters selection strategy based on the quantile forecasts distribution is proposed to improve the results. A secondary contribution is to use a recently developed deep learning model known as normalizing flows to generate quantile forecasts of renewable generation for the robust optimization problem. This technique provides a general mechanism for defining expressive probability distributions, only requiring the specification of a base distribution and a series of bijective transformations. Overall, the robust approach improves the results over a deterministic approach with nominal point forecasts by finding a trade-off between conservative and risk-seeking policies. The case study uses the photovoltaic generation monitored on-site at the University of Liège (ULiège), Belgium.

stat.AP↗

arXiv2021

A deep generative model for probabilistic energy forecasting in power systems: normalizing flows

Greater direct electrification of end-use sectors with a higher share of renewables is one of the pillars to power a carbon-neutral society by 2050. However, in contrast to conventional power plants, renewable energy is subject to uncertainty raising challenges for their interaction with power systems. Scenario-based probabilistic forecasting models have become a vital tool to equip decision-makers. This paper presents to the power systems forecasting practitioners a recent deep learning technique, the normalizing flows, to produce accurate scenario-based probabilistic forecasts that are crucial to face the new challenges in power systems applications. The strength of this technique is to directly learn the stochastic multivariate distribution of the underlying process by maximizing the likelihood. Through comprehensive empirical evaluations using the open data of the Global Energy Forecasting Competition 2014, we demonstrate that this methodology is competitive with other state-of-the-art deep learning generative models: generative adversarial networks and variational autoencoders. The models producing weather-based wind, solar power, and load scenarios are properly compared in terms of forecast value by considering the case study of an energy retailer and quality using several complementary metrics. The numerical experiments are simple and easily reproducible. Thus, we hope it will encourage other forecasting practitioners to test and use normalizing flows in power system applications such as bidding on electricity markets, scheduling power systems with high renewable energy sources penetration, energy management of virtual power plan or microgrids, and unit commitment.

cs.LG↗

arXiv2021

Probabilistic Forecasting of Imbalance Prices in the Belgian Context

Forecasting imbalance prices is essential for strategic participation in the short-term energy markets. A novel two-step probabilistic approach is proposed, with a particular focus on the Belgian case. The first step consists of computing the net regulation volume state transition probabilities. It is modeled as a matrix computed using historical data. This matrix is then used to infer the imbalance prices since the net regulation volume can be related to the level of reserves activated and the corresponding marginal prices for each activation level are published by the Belgian Transmission System Operator one day before electricity delivery. This approach is compared to a deterministic model, a multi-layer perceptron, and a widely used probabilistic technique, Gaussian Processes.

q-fin.ST↗

arXiv2021

Deep learning-based multi-output quantile forecasting of PV generation

This paper develops probabilistic PV forecasters by taking advantage of recent breakthroughs in deep learning. It tailored forecasting tool, named encoder-decoder, is implemented to compute intraday multi-output PV quantiles forecasts to efficiently capture the time correlation. The models are trained using quantile regression, a non-parametric approach that assumes no prior knowledge of the probabilistic forecasting distribution. The case study is composed of PV production monitored on-site at the University of Liège (ULiège), Belgium. The weather forecasts from the regional climate model provided by the Laboratory of Climatology are used as inputs of the deep learning models. The forecast quality is quantitatively assessed by the continuous ranked probability and interval scores. The results indicate this architecture improves the forecast quality and is computationally efficient to be incorporated in an intraday decision-making tool for robust optimization.

cs.LG↗

arXiv2021

Coordination of operational planning and real-time optimization in microgrids

Hierarchical microgrid control levels range from distributed device level controllers that run at a high frequency to centralized controllers optimizing market integration that run much less frequently. Centralized controllers are often subdivided into operational planning controllers that optimize decisions over a time horizon of one or several days, and real-time optimization controllers that deal with actions in the current market period. The coordination of these levels is of paramount importance. In this paper, we propose a value function-based approach as a way to propagate information from operational planning to real-time optimization. We apply this method to an environment where operational planning, using day-ahead forecasts, optimizes at a market period resolution the decisions to minimize the total energy cost and revenues, the peak consumption and injection-related costs, and plans for reserve requirements. While real-time optimization copes with the forecast errors and yields implementable actions based on real-time measurements. The approach is compared to a rule-based controller on three use cases, and its sensitivity to forecast error is assessed.

eess.SY↗

arXiv2021

Stochastic and deterministic formulations for capacity firming nominations

This paper addresses the energy management of a grid-connected photovoltaic plant coupled with a battery energy storage device, within the capacity firming specifications of the French Energy Regulatory Commission. The paper contributions are positioned in the continuity of the studies adopting stochastic models for optimizing the bids of renewable energy sources in a day-ahead market by considering a storage device. The proposed deterministic and stochastic approaches are optimization problems formulated as quadratic problems with linear constraints. The case study is a real microgrid with PV production monitored on-site. The results demonstrate the validity of the stochastic formulation by using an ideal predictor that produces unbiased PV scenarios.

math.OC↗

arXiv2021

Probabilistic forecasting for sizing in the capacity firming framework

This paper proposes a strategy to size a grid-connected photovoltaic plant coupled with a battery energy storage device within the \textit{capacity firming} specifications of the French Energy Regulatory Commission. In this context, the sizing problem is challenging due to the two-phase engagement control with a day-ahead nomination and an intraday control to minimize deviations from the planning. The two-phase engagement control is modeled with deterministic and stochastic approaches. The optimization problems are formulated as mixed-integer quadratic problems, using a Gaussian copula methodology to generate PV scenarios, to approximate the mixed-integer non-linear problem of the capacity firming. Then, a grid search is conducted to approximate the optimal sizing for a given selling price using both the deterministic and stochastic approaches. The case study is composed of PV production monitored on-site at the Liège University (ULiège), Belgium.

math.OC↗

arXiv2020

Classification of load forecasting studies by forecasting problem to select load forecasting techniques and methodologies

The key contribution of this paper is to propose a classification into two dimensions of the load forecasting studies to decide which forecasting tools to use in which case. This classification aims to provide a synthetic view of the relevant forecasting techniques and methodologies by forecasting problem. In addition, the key principles of the main techniques and methodologies used are summarized along with the reviews of these papers. The classification process relies on two couples of parameters that define a forecasting problem. Each article is classified with key information about the dataset used and the forecasting tools implemented: the forecasting techniques (probabilistic or deterministic) and methodologies, the data cleansing techniques, and the error metrics. The process to select the articles reviewed in this paper was conducted into two steps. First, a set of load forecasting studies was built based on relevant load forecasting reviews and forecasting competitions. The second step consisted in selecting the most relevant studies of this set based on the following criteria: the quality of the description of the forecasting techniques and methodologies implemented, the description of the results, and the contributions. This paper can be read in two passes. The first one by identifying the forecasting problem of interest to select the corresponding class into one of the four classification tables. Each one references all the articles classified across a forecasting horizon. They provide a synthetic view of the forecasting tools used by articles addressing similar forecasting problems. Then, a second level composed of four Tables summarizes key information about the forecasting tools and the results of these studies. The second pass consists in reading the key principles of the main techniques and methodologies of interest and the reviews of the articles.

cs.IR↗