Search

The relationship between electricity demand and weather has been established for a long time and is one of the cornerstones in load prediction for operation and planning, along with behavioral and social aspects such as calendars or significant events. This paper explores how and why the social information contained in the news can be used better to understand aggregate population behaviour in terms of energy demand. The work is done through experiments analysing the impact of predicting features extracted from national news on day-ahead electric demand prediction. The results are compared to a benchmark model trained exclusively on the calendar and meteorological information. Experimental results showed that the best-performing model reduced the official standard errors around 4%, 11%, and 10% in terms of RMSE, MAE, and SMAPE. The best-performing methods are: word frequency identified COVID-19-related keywords; topic distribution that identified news on the pandemic and internal politics; global word embeddings that identified news about international conflicts. This study brings a new perspective to traditional electricity demand analysis and confirms the feasibility of improving its predictions with unstructured information contained in texts, with potential consequences in sociology and economics., 10 pages, 6 figures, 5 tables

This document summarises the findings of the REgions project on the limitations identified for the supply of network services from a Virtual Power Plant of distributed Renewable Energy Sources. These are divided mainly among Technical and Regulatory barriers. The report continues defining Guidelines and finish with a plan for a final dissemination to stakeholders. Among the technical barriers, it is possible to mention 1) the ones related to Market Access, 2) the challenges for scaling up the solution and the interoperability among the solutions of different vendors in absence of standardisation, 3) the characteristics of service provision and finally 4) issues related to ITC resilience and security. Among the regulatory barriers, a focus is made on the situation in Austria, as an example of a typical European country, and attention is paid to: 1) the subsidy regime for renewables and 2) the support for new installation and 3) for existing installations. Guidelines cover mainly the 1) provision of redispatch, of 2) balancing, with attention to the distortions introduced by current subsidies and 3) the provision of demand response. Finally, an analysis is given considering the current energy crisis.

This paper presents the results of a series of tests on the provision of ancillary services by a Virtual Power Plant composed of variable Renewable Energy Resources. The ancillary services provided are Frequency Containment Reserve and Frequency Restoration Reserve, roughly primary and secondary reserve, and the resources used by the virtual power plant were wind and photovoltaics plant for a total of 273 MW of installed power on 17 generators. Renewable dispatchable units such as batteries, hydro or biomass were not considered in order to quantify the performance with the most critical generation technologies. Symmetric reserve activation of up to 10 MW. The quality of the reserve delivery was measured according to purpose-developed metrics and telecommunication failures were considered the main source of errors.

International audience; Short-term forecasting is key to the safe, reliable, and economic operation of modern power systems. As the majority of modern forecasting tools are purely data-driven, their performance relies heavily on the quality and availability of data. In this work, we examine forecasting when a subset of features used during model training becomes unavailable (deleted or missing) in an operational setting, a subject that has been largely overlooked by previous works. Several reasons could lead to feature deletion, including malicious data-integrity attacks, network latency, and equipment malfunctions, among others. We leverage tools from robust optimization and machine learning and formulate a linear regression model that is optimally resilient to the deletion of features at test time. The robust counterpart of the proposed model is a linear program whose size grows polynomially with the number of training observations and the number of features; we further provide a decomposition algorithm based on the alternating direction method of multipliers to deal with large problem instances that are typically found in energy forecasting applications. We further extend to the case of Probabilistic Forecasting by robustifying the standard linear quantile regression model. To validate empirically the proposed approach, we examine several prevalent forecasting practices in power systems, namely electricity prices, load, wind production, and solar production forecasting. We compare against regularized and randomization-based models and benchmark their performance for the case of feature deletion. The results show that the proposed solution successfully mitigates the adverse effects of missing features, leading to the lowest overall performance degradation. Further, it successfully hedges against the most adverse scenario of deleting the most important feature from the test set. The results persist both for point and probabilistic forecasts and across the different series. Overall, this work highlights the benefits of leveraging robust optimization and provides a new perspective on how to deal with feature uncertainty in energy forecasting applications.

International audience; (200 w) The fall in price for PV systems and the democratisation of electricity storage technology there is an increased interest in hybrid photovoltaic and battery systems. In interconnected applications, their operating cost must be competitive concerning the power supplied by the grid when no additional services are considered. This work presents the findings of a study on the optimal sizing of residential HPVB systems in Europe, considering the climatic and financial characteristics of each country. The study analyses also the temperature impact on battery ageing and its importance on system sizing.

Decision-making in the presence of contextual information is a ubiquitous problem in modern power systems. The typical data-decisions pipeline comprises several forecasting and optimization components deployed in sequence. However, the loss function employed during learning is only a proxy for task-specific costs (e.g. scheduling, trading). This work describes a data-driven alternative to improve prescriptive performance in conditional stochastic optimization problems based on nonparametric machine learning. Specifically, we propose prescriptive trees that minimize task-specific costs during learning, embedded with a scenario reduction procedure to reduce computations, and then derive a weighted Sample Average Approximation of the original problem. We present experimental results for two problems: storage scheduling for price arbitrage and networkconstrained stochastic market clearing, respectively associated with electricity price and load forecasting. The empirical results show significant improvements on deterministic and stochastic lookahead policies, with the relative difference being more pronounced when training data are limited.

International audience; In this paper, the authors start by introducing and explaining the concept behind the market business model which was developed and tested during SENSIBLE project. This use case is based on three main pillars: forecasts, distribution system operator tools and retailer requests. The aim of this use case was to define a possible framework and validate its technical feasibility in a real environment.