Paweł Kobyliński, Mariusz Wierzbowski, Cezary Biele
2018 W: Intelligent Human Systems Integration : Proceedings of the 1st International Conference on Intelligent Human Systems Integration (IHSI 2018): Integrating People and Intelligent Systems, January 7–9, 2018, Dubai, United Arab Emirates / Tareq Ahram, Waldemar Karwowski; Cham: Springer, s. 131-136
The paper aims at reporting lessons learnt while addressing issues concerning modelling energy load prediction for (1) a real small neighbourhood (circa 70 households) and (2) real individual households. The results should be of concern to engineers designing energy balancing systems for small smart energy grids. The endeavour of modelling and implementing 24 h energy load profile prediction in 15 min resolution turned out successful at neighbourhood level. However, at individual household level the modelling encountered important obstacles of objective nature. The uncertainties introduced into energy load profiles by randomly timed human behaviour at a single level can (1) limit or (2) virtually preclude efficient energy load profile prediction. The paper differentiates between the first and the second possibilities by describing two types of stochastic components representing randomly timed human factor.