A5062263776- Electric Power System Optimization
- Energy Load and Power Forecasting
- Smart Grid Energy Management
- Optimal Power Flow Distribution
- Power System Reliability and Maintenance
- Market Dynamics and Volatility
- Building Energy and Comfort Optimization
- Auction Theory and Applications
- Integrated Energy Systems Optimization
- Time Series Analysis and Forecasting
- Green IT and Sustainability
- Power System Optimization and Stability
- Microgrid Control and Optimization
- Chronic Disease Management Strategies
- Grey System Theory Applications
- Adversarial Robustness in Machine Learning
- Explainable Artificial Intelligence (XAI)
- Meteorological Phenomena and Simulations
- Global Health Care Issues
- COVID-19 impact on air quality
- Network Security and Intrusion Detection
- Energy Efficiency and Management
- Advanced Neural Network Applications
- Capital Investment and Risk Analysis
- Fire dynamics and safety research
Comillas Pontifical University
2013-2024
Non-intrusive load monitoring (NILM) has become an important subject of study, since it provides benefits to both consumers and utility companies. The analysis smart meter signals is useful for identifying consumption patterns user behaviors, in order make predictions optimizations anticipate the use electrical appliances at home. However, problem with this kind rests how isolate individual from aggregated signal. In work, we propose unsupervised disaggregation method based on a controlled...
The deployment of microgrids could be fostered by control systems that do not require very complex modelling, calibration, prediction and/or optimisation processes. This paper explores the application Reinforcement Learning (RL) techniques for operation a microgrid. implemented Deep Q-Network (DQN) can learn an optimal policy elements isolated microgrid, based on interaction agent-environment when particular actions are taken in microgrid components. In order to facilitate scaling-up this...
Flexibility of distributed energy resources is increasingly needed in the electricity markets and grids. But this dispersed flexibility can be used efficiently only if it aggregated to wholesale market products. A set software tools was developed for an actor or a company who aggregates flexible household demand network operators. The comprise 1) short term forecasting prices, 2) loads their responses control signals, 3) optimal selection signals consequently also each situation, 4) relevant...
This paper studies an approach to identify representative operating and contingency (OC) scenarios for the design of underfrequency load-shedding (UFLS) schemes. In small isolated power systems, are outages generating units. Usually, only N-1 considered. this paper, simultaneous several units also taken into account. Data mining techniques such as K-Means Fuzzy C-Means algorithms used group in terms system frequency OC scenarios. The has been applied UFLS schemes two Spanish systems. results...
Electricity markets are based on several sequential energy and reserve trading mechanisms to constantly maintain the balance between generation demand. During last years, getting much importance all around world with increasing social awareness of renewable benefits. Additional quantities larger remunerations being implemented by regulators since this is highly dependent weather conditions uncertainties. Utilities therefore demanding more powerful models better optimize their bidding curves...
Background: The COVID-19 pandemic has had global effects; cases have been counted in the tens of millions, and there over two million deaths throughout world. Health systems stressed trying to provide a response increasing demand for hospital beds during different waves. This paper analyzes dynamic hospitals Community Madrid (CoM) first wave severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) period between 18 March 31 May 2020. aim was model CoM’s health system terms number...
Residual demand curves (RDCs) can be used to represent the strategic interaction of participants in electricity markets. RDCs relate energy that an agent buy or sell one hour with clearing market price would obtained such hour, assuming is organized as simple bid independent auctions. Despite fact they have been widely literature, existence time and/or spatial constraints algorithm makes not directly applicable. This paper tries overcome these difficulties by extending concept zonal pricing...
The Linear Hinges Model (LHM) is an efficient approach to flexible and robust one-dimensional curve fitting under stringent high-noise conditions. However, it was initially designed run in a single-core processor, accessing the whole input dataset. surge data volumes, coupled with increase parallel hardware architectures specialised frameworks, has led growth interest need for new algorithms able deal large-scale datasets techniques adapt traditional machine learning this paradigm. This...
This paper describes SGO, a management information system for bidding in deregulated electricity markets, developed the Spanish case. SGO has client-server architecture and consists of set integrated cooperative flexible software tools assisting users during whole process: resources identification, bids generation, market performance characterisation, strategy analysis optimisation, generation markets results reports automatic monitoring suggesting on-line corrective actions.
Temperature is widely known as one of the most important drivers to forecast electricity and gas variables, such load. Because that reason, temperature forecasting has been for years great interest energy forecasters several approaches methods have published. However, these usually do not consider trend, which causes error increases when dealing with medium- or long-term estimations. This paper presents based on time series decomposition analyzes their results trends 37 different European...
The power sector is a major contributor to anthropogenic global warming and responsible for 38% of total energy-related carbon dioxide emissions 66% emission growth in 2018. In OECD member countries, the residential consumes significant amount electrical energy, with household refrigerating appliances alone accounting 30–40% consumption. To analyze energy use each domestic appliance, researchers have developed Appliance-Level Energy Characterization (ALEC), set techniques that provide...
Due to the large size of electric power systems, there is a very high computational burden when obtaining optimum network by using classical optimization techniques. Several authors have used heuristics and/or sensitivities in order guide search optimal investments. This paper proposes an automatic learning approach decide whether change will improve overall costs or not. More specifically, decision trees methods are identify set simple and reliable rules which combine criteria based on both...
BREACH is a side-channel attack to HTTPS that allows an attacker obtain victims' credentials under certain conditions.An with privileged position on the network can guess character by secret session key just analyzing size of responses returned server over and encrypted.Heal Breach (HTB) proposed technique mitigate randomly changing through modified gzip library.The needs precision one byte in be able determine if part token.Since library introduces randomness response, becomes...
Purpose The purpose of this paper is to analyze medium‐term risks faced by electrical generation companies in competitive environments. Market are caused several variables subject uncertainty. Hydro conditions, fuel (coal and natural gas) prices, system demand, CO 2 emission price the risk factors considered paper. Taking into account these factors, have take decisions that would affect their economic results exposure. Design/methodology/approach This proposes a methodology support...
With the increasing penetration of intermittent technologies, such as renewable energy sources, electricity secondary (spinning) reserve markets are getting much relevance all around world to constantly maintain balance between generation and demand. In this new context, utilities increasingly demanding powerful tools better optimize their bidding curves, trying maximize benefits while satisfying system necessities published by System Operators. This paper describes three integer...
Background Functional impairment is one of the most decisive prognostic factors in patients with complex chronic diseases. A more significant functional indicates that disease progressing, which requires implementing diagnostic and therapeutic actions stop exacerbation disease. Objective This study aimed to predict alterations clinical condition diseases by predicting Barthel Index (BI), assess their status using an artificial intelligence model data collected through internet things...