Loading...
4 results
Search Results
Now showing 1 - 4 of 4
- A Machine Learning Model for Procurement of Secondary Reserve Capacity in Power Systems with Significant vRES PenetrationsPublication . dos Santos, Joao; Algarvio, HugoABSTRACT: The growing investment in variable renewable energy sources is changing how electricity markets operate. In Europe, players rely on forecasts to participate in day-ahead markets closing between 12 and 37 h ahead of real-time operation. Usually, transmission system operators use a symmetrical procurement of up and down secondary power reserves based on the expected demand. This work uses machine learning techniques that dynamically compute it using the day-ahead programmed and expected dispatches of variable renewable energy sources, demand, and other technologies. Specifically, the methodology incorporates neural networks, such as Long Short-Term Memory (LSTM) or Convolutional neural network (CNN) models, to improve forecasting accuracy by capturing temporal dependencies and nonlinear patterns in the data. This study uses operational open data from the Spanish operator from 2014 to 2023 for training. Benchmark and test data are from the year 2024. Different machine learning architectures have been tested, but a Fully Connected Neural Network (FCNN) has the best results. The proposed methodology improves the usage of the up and down secondary reserved power by almost 22% and 11%, respectively.
- Pre-Solve Methodologies for Short-Run Identification of Critical Sectors in the ACSR Overhead Lines While Using Dynamic Line Rating Models for Resource SustainabilityPublication . Algarvio, HugoABSTRACT: Most transmission system operators (TSOs) use seasonally static models considering extreme weather conditions, serving as a reference for computing the transmission capacity of power lines. The use of dynamic line rating (DLR) models can avoid the construction of new lines, market splitting, false congestions and the degradation of lines in a cost-effective way. The operation of power systems is planned based on market results, which consider transactions hours ahead of real-time operation using forecasts with errors. The same is true for the DLR. So, during real-time operation TSOs should rapidly compute the DLR of overhead lines to avoid considering an ampacity above their lines' design, reflecting the real-time weather conditions. Considering that the DLR of the lines can affect the power flow of an entire region, the use of the complete indirect DLR methodology has a high computation burden for all sectors and lines in a region. So, this article presents and tests three pre-solve methodologies able to rapidly identify the critical sector of each line. These methodologies solve the problem of the high computation burden of the CIGR & Eacute; thermodynamic model of overhead lines. They have been tested by using real data of the transmission grid and the weather conditions for two different regions in Portugal, leading to errors in the computation of the DLR lower than 1% in relation to the complete CIGR & Eacute; model, identifying the critical sector in significantly less time.
- Strategic Bidding to Increase the Market Value of Variable Renewable Generators in Electricity MarketsPublication . Sousa, Vivian; Algarvio, HugoABSTRACT: The 2050 global ambition for a carbon-neutral society is increasing the penetration of the most competitive variable renewable technologies, onshore wind and solar PV. These technologies are known for their near-zero marginal costs but highly variable time-dependent generation. Power systems with major penetrations of variable generation need high balancing flexibility to guarantee their stability by maintaining the equilibrium between demand and supply. Electricity markets were designed for dispatchable technologies. Support schemes are used to incentivize and de-risk the investment in variable renewables, since actual market designs are riskier for their active participation. This study presents three strategic bidding strategies for the active participation of variable renewables in electricity markets based on probabilistic quantile-based forecasts. This case study examines the levels of active market participation for a wind power producer (WPP) in the Iberian electricity market and the Portuguese balancing markets, where WPPs are financially responsible for imbalances and operate without support schemes in the first and second stages of the Iberian market designs. Results from this study indicate that the WPP has the potential to increase its market value between 36% and 155% if participating in the tertiary and secondary balancing markets completely adapted to its design, respectively. However, considering the use of strategic bidding in actual market designs, by participating in the secondary reserve, the WPP can increase its market value by 10% and 45% when compared with perfect foresight and operational cases, respectively.
- Strategies to Incentivize the Participation of Variable Renewable Energy Generators in Balancing MarketsPublication . Algarvio, Hugo; Sousa, VivianABSTRACT: Balancing markets (BMs) play a crucial role in ensuring the real-time equilibrium between electricity demand and supply. The current requirements for participation in BMs often overlook the characteristics and capabilities of variable renewables, limiting their effective integration. The increasing penetration of variable renewables necessitates adjustments in the design of BMs to support the transition toward carbon-neutral power systems. This study examines the levels of active market participation for a wind power producer (WPP) in the Iberian Electricity Market and the Portuguese BMs. In addition to exploring current market dynamics, the study tests one methodology proposed by the Danish Transmission System Operator to support the participation of variable renewables in BMs, the P90, and two new methods based on the full cost balancing concept. These methodologies incentivize WPPs to minimize imbalances by allowing market participation only if imbalances remain within a 10% deadband of annual hours (P90), hourly offers (D90), or both (DP90). The results indicate that participating in the secondary capacity market, particularly for downward capacity, is the most profitable strategy. This participation enhances the value of wind power by over 42%. However, in most methodologies, the WPP failed to deliver nearly 100% of its allocated capacity approximately 1% of the time. In contrast, the D90 approach limited the maximum deviation to 10%, demonstrating the highest reliability among the evaluated methods.