Examinando por Autor "Kamara Esteban, Oihane"

Mostrando 1 - 3 de 3
  • Miniatura
    Ítem
    Contributions to demand-side management by the application of artificial intelligence techniques in domestic, commercial and industrial scenarios
    (Universidad de Deusto, 2017-09-22) Kamara Esteban, Oihane; Macarulla, Ana María; Borges Hernández, Cruz E.; Facultad de Ingeniería; Ingeniería Informática y Telecomunicación
    Electricity is, perhaps, the most identifiable and ubiquitous form of energy. Whether we are watching a movie, preparing dinner, working on the computer, manufacturing the engine of a car, using an elevator, or just reading the news feed on our mobile phone, electricity is always present either directly or indirectly. Trends in electricity consumption worldwide show that the global demand is expected to grow significantly in the forthcoming years driven, primarily, by the development of new technologies that help achieve a higher quality of life. In fact, the shift of worldwide economies from a subsistence perspective to industrial or service approaches, specially in developing countries, is what is leading the growth in electricity needs. Electricity is considered a secondary energy source since it is obtained from the transformation of primary sources of energy, either renewable or non-renewable. Even though renewable technologies are slowly but steadily gaining ground as a clean and cost-effective generation alternative, the vast majority of the world’s electricity is still being produced from non-renewable sources, such as coal, gas, or oil. In fact, if we analyse CO2 emissions related to energy generation, the electricity sector is responsible for around 40% of these emissions due to the use of fossil sources for electricity generation. This growth scenario calls for the design and implementation of energy efficiency measures that ensure a reliable and adequate electricity supply that meets the global demand at all times, while reducing the greenhousegas emissions derived from its generation. Among these efficiency measures, the most favoured by electric utilities due to its cost-effectiveness and immediacy of results is Demand-Side Management. Demand-Side Management strategies are actions designed to modify the behaviour of the customers in regards to the the amount and timing of electricity use for the collective benefit of the society and the utility. The emergence and settlement of the Smart Grid and associated smart devices have encouraged the implementation of these type of programs, thanks to the availability of real-time consumption data through intelligent monitoring and the possibility to manage the whole grid. The thesis presented below comprehends the research done to push forward the State of the Art of Demand-Side Management. We have identified the research opportunities from a vertical perspective: analysing the needs and best practice to standardise the communication of the devices that are part of the Smart Grid, highlighting the advantages of creating simulation scenarios that will help electric utilities to take decisions prior to physical or logical deployment of network elements, and finally, demonstrating cases of application of Artificial Intelligence techniques to implement Demand-Side Management in domestic, commercial, and industrial scenarios.
  • Miniatura
    Ítem
    Enhancing the missing data imputation of primary substation load demand records
    (Elsevier Ltd, 2020-06-23) Borges Hernández, Cruz E.; Kamara Esteban, Oihane; Castillo Calzadilla, Tony; Martín Andonegui, Cristina; Alonso Vicario, Ainhoa
    The daily analysis of loads is one of the most important activities for power utilities in order to be able to meet the energy demand. This analysis not only includes short-term forecasting but it also encompasses the completion of missing load data, known as imputation. In this work we show that adding information of attached or bordering primary substation helps to improve the prediction accuracy in a single substation, since its neighbours may share common weather-related (e.g. temperature, humidity, wind direction, etc.) and human-related (e.g. work-calendar, holidays, cultural consumption patterns, etc.) data. In order to validate these approaches, we test the forecasting and imputation neighbouring methodology on a wide variety of datasets. Results confirm that, given a primary substation, the addition of information from surrounding substations does improve the forecasting and imputation errors.
  • Miniatura
    Ítem
    Socio-economic effect on ICT-based persuasive interventions towards energy efficiency in tertiary buildings
    (MDPI AG, 2020-04-03) Casado Mansilla, Diego; Tsolakis, Apostolos C. ; Borges Hernández, Cruz E.; Kamara Esteban, Oihane; Krinidis, Stelios; Ávila, José Manuel; Tzovaras, Dimitrios; López de Ipiña González de Artaza, Diego
    Occupants of tertiary environments rarely care about their energy consumption. This fact is even more accentuated in cases of buildings of public use. Such unawareness has been identified by many scholars as one of the main untapped opportunities with high energy saving potential in terms of cost-effectiveness. Towards that direction, there have been numerous studies exploring energy-related behaviour and the impact that our daily actions have on energy efficiency, demand response and flexibility of power systems. Nevertheless, there are still certain aspects that remain controversial and unidentified, especially in terms of socio-economic characteristics of the occupants with regards to bespoke tailored motivational and awareness-based campaigns. The presented work introduces a two-step survey, publicly available through Zenodo repository that covers social, economic, behavioural and demographic factors. The survey analysis aims to fully depict the drivers that affect occupant energy-related behaviour at tertiary buildings and the barriers which may hinder green actions. Moreover, the survey reports evidence on respondents' self-assessment of fifteen known principles of persuasion intended to motivate them to behave pro-environmentally. The outcomes from the self-assessment help to shed light on understanding which of the Persuasive Principles may work better to nudge different user profiles towards doing greener actions at workplace. This study was conducted in four EU countries, six different cities and seven buildings, reaching more than three-hundred-and-fifty people. Specifically, a questionnaire was delivered before (PRE) and after (POST) a recommendation-based intervention towards pro-environmental behaviour through Information and Communication Technologies (ICT). The findings from the PRE-pilot stage were used to refine the POST-pilot survey (e.g., we removed some questions that did not add value to one or several research questions or dismissed the assessment of Persuasive Principles (PPs) which were of low value to respondents in the pre-pilot survey). Both surveys validate "Cause and Effect", "Conditioning" and "Self-monitoring" as the top PPs for affecting energy-related behaviour in a workplace context. Among other results, the descriptive and prescriptive analysis reveals the association effects of specific barriers, pro-environmental intentions and confidence in technology on forming new pro-environmental behaviour. The results of this study intend to set the foundations for future interventions based on persuasion through ICT to reduce unnecessary energy consumption. Among all types of tertiary buildings, we emphasise on the validity of the results provided for buildings of public use.