Alexandre Lucas

Alexandre Lucas


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 October 2020 in Energies
Verified
Journal Article
Open access
PDF file
ALAlexandre Lucas
Alexandre Lucas
KPKonstantinos Pegios
Konstantinos Pegios
Evangelos KotsakisEvangelos Kotsakis
Evangelos Kotsakis
DCDan Clarke
Dan Clarke
The importance of price forecasting has gained attention over the last few years, with the growth of aggregators and the general opening of the European electricity markets. Market participants manage a tradeoff between, bidding in a lower price market (day-ahead), but with typically higher volume, or aiming for a lower volume market but with potentially higher returns (balance energy market). Companies try to forecast the extremes of revenues or prices, in order to manage risk and opportunity, assigning their assets in an optimal way. It is thought that in general, electricity markets have quasi-deterministic principles, rather than being based on speculation, hence the desire to forecast the price based on variables that can describe the outcome of the market. Many studies address this problem from a statistical approach or by performing multiple-variable regressions, but they very often focus only on the time series analysis. In 2019, the Loss of Load Probability (LOLP) was made available in the UK for the first time. Taking this opportunity, this study focusses on five LOLP variables (with different time-ahead estimations) and other quasi-deterministic variables, to explain the price behavior of a multi-variable regression model. These include base production, system load, solar and wind generation, seasonality, day-ahead price and imbalance volume contributions. Three machine-learning algorithms were applied to test for performance, Gradient Boosting (GB), Random Forest (RF) and XGBoost. XGBoost presented higher performance and so it was chosen for the implementation of the real time forecast step. The model returns a Mean Absolute Error (MAE) of 7.89 £/MWh, a coefficient of determination (R2 score) of 76.8% and a Mean Squared Error (MSE) of 124.74. The variables that contribute the most to the model are the Net Imbalance Volume, the LOLP (aggregated), the month and the De-rated margins (aggregated) with 28.6%, 27.5%, 14.0%, and 8.9% of weight on feature importance respectively.

29 March 2021 in Energies
Verified
Journal Article
Open access
PDF file
ALAlexandre Lucas
Alexandre Lucas
DGDimitrios Geneiatakis
Dimitrios Geneiatakis
YSYannis Soupionis
Yannis Soupionis
INIgor Nai-Fovino
Igor Nai-Fovino
Evangelos KotsakisEvangelos Kotsakis
Evangelos Kotsakis
Demand response (DR) services have the potential to enable large penetration of renewable energy by adjusting load consumption, thus providing balancing support to the grid. The success of such load flexibility provided by industry, communities, or prosumers and its integration in electricity markets, will depend on a redesign and adaptation of the current interactions between participants. New challenges are, however, bound to appear with the large scale contribution of smaller assets to flexibility, including, among others, the dispatch coordination, the validation of delivery of the DR provision, and the corresponding settlement of contracts, while assuring secured data access among interested parties. In this study we applied distributed ledger (DLT)/blockchain technology to securely track DR provision, focusing on the validation aspect, assuring data integrity, origin, fast registry, and sharing within a permissioned system, between all relevant parties (including transmission system operators (TSOs), aggregators, distribution system operators (DSOs), balance responsible parties (BRP), and prosumers). We propose a framework for DR registry and implemented it as a proof of concept on Hyperledger Fabric, using real assets in a laboratory environment, in order to study its feasibility and performance. The lab set up includes a 450 kW energy storage system, scheduled to provide DR services, upon a system operator request and the corresponding validations and verifications are done, followed by the publication on a blockchain. Results show the end to end execution time remained below 1 s, when below 32 requests/sec. The smart contract memory utilization did not surpass 1% for both active and passive nodes and the peer CPU utilization, remained below 5% in all cases simulated (3, 10, and 28 nodes). Smart Contract CPU utilization remained stable, below 1% in all cases. The performance of the implementation showed scalable results, which enables real world adoption of DLT in supporting the development of flexibility markets, with the advantages of blockchain technology.