Surrogate Estimators for Complex Bi-Level Energy Management
Alain Quilliot, Fatiha Bendali, Jean Mailfert, Eloise Mole Kamga, Alejandro Olivas Gonzalez, Hélène Toussaint
DOI: http://dx.doi.org/10.15439/2022F19
Citation: Communication Papers of the 17th Conference on Computer Science and Intelligence Systems, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 32, pages 85–92 (2022)
Abstract. We deal here with the routing of vehicles in charge of performing internal logistics tasks inside some protected area. Those vehicles are provided in energy by a local solar hydrogen production facility, with limited storage and time-dependent production capacities. In order to avoid importing energy from outside, one wants to synchronize energy production and consumption in order ot minimize both production and routing costs. Because of the complexity of resulting bi-level model, we deal with it by short-cutting the production scheduling level with the help of surrogate estimators, whose values are estimated through fast dynamic programming algorithms or through machine learning.