This module receives several attributes as input such as the latitude and longitude of the solar panel, the tilt angle, the total area of the solar panel and additional characteristics of the panel, in order to produce the energy generation forecast of the solar panel installation for the next day.
This module focuses on HVAC modules of a building or group of buildings and utilizes building related data, such as its coordinates, as well as HVAC energy consumption data (both historical and real-time), in order to produce a forecast regarding the HVAC’ energy demand, for the next day.
This component utilizes the PV generation forecasting and input collected by the user regarding energy-intensive activities, in order to provide as output a suggestion aiming at maximization of RES penetration, through the suggestion of a new schedule of the various activities.
The services delivered through the e-PIOTIS project make use of state of the art Artificial Intelligence and Machine Learning approaches, to utilize models and train data from a wide variety of buildings, in order to conduct accurate forecasts, utilizing already available data and training through open datasets. APIs and open technologies such as Docker are adopted to deliver standalone open-source components.
is a co-funded cascading funding project funded under the PLATOON (Digital PLAtform and analytic TOOls for eNergy) series of Open Calls, which aims to digitalise the energy sector, enabling thus higher levels of operational excellence with the adoption of disrupting technologies
More Info