Browsing by Keyword "Forecasting"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Optimised TSO-DSO Coordination to Integrate Renewables in Flexibility Markets(IEEE, 2019-09) Madina, Carlos; Kuusela, Pirkko; Rossi, Marco; Aghaie, Hamid; Gomez-Arriola, Ines; Riaño, Sandra; POWER SYSTEMS; SISTEMAS FOTOVOLTAICOSThe necessary energy transition to decarbonize power systems is leading to increasingly important challenges for the operation of power systems. On the one hand, the intermittent nature of renewable generation requires system operators to procure ancillary services in larger volumes than in the past. On the other, the growing penetration of medium- and small-scale, flexible demand and storage systems in distribution networks could potentially offer network services, if they are aggregated effectively and there is an appropriate coordination between transmission system operators (TSOs), distribution system operators (DSOs) and aggregators. Therefore, an important topic to be analysed is whether distributed energy resources (DER) can replace traditional generation in the provision of ancillary services (AS), how this replacement will affect the system operators’ roles and how to improve the coordination between TSOs and DSOs. This paper shows the results of the cost-benefit analysis (CBA) performed within the project SmartNet to assess the advantages or disadvantages of different TSO-DSO coordination schemes, as well as the follow-up activities to be carried out in the project CoordiNet.Item Transfer Learning and Online Learning for Traffic Forecasting under Different Data Availability Conditions: Alternatives and Pitfalls(Institute of Electrical and Electronics Engineers Inc., 2020-09-20) Manibardo, Eric L.; Laña, Ibai; Del Ser, Javier; IAThis work aims at unveiling the potential of Transfer Learning (TL) for developing a traffic flow forecasting model in scenarios of absent data. Knowledge transfer from high-quality predictive models becomes feasible under the TL paradigm, enabling the generation of new proper models with few data. In order to explore this capability, we identify three different levels of data absent scenarios, where TL techniques are applied among Deep Learning (DL) methods for traffic forecasting. Then, traditional batch learning is compared against TL based models using real traffic flow data, collected by deployed loops managed by the City Council of Madrid (Spain). In addition, we apply Online Learning (OL) techniques, where model receives an update after each prediction, in order to adapt to traffic flow trend changes and incrementally learn from new incoming traffic data. The obtained experimental results shed light on the advantages of transfer and online learning for traffic flow forecasting, and draw practical insights on their interplay with the amount of available training data at the location of interest.