Contributions to demand-side management by the application of artificial intelligence techniques in domestic, commercial and industrial scenarios

Resumen

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.