| Title |
A Control Strategy Based On Power Forecasting For Micro-Grid Systems |
| ID_Doc |
1095 |
| Authors |
Elmouatamid A.; Ouladsine R.; Bakhouya M.; El Kamoun N.; Zine-Dine K.; Khaidar M. |
| Year |
2019 |
| Published |
5th IEEE International Smart Cities Conference, ISC2 2019 |
| DOI |
http://dx.doi.org/10.1109/ISC246665.2019.9071722 |
| Abstract |
Balancing production and demand of energy is the main challenge to integrate renewable energy sources (RES) in micro-grid (MG) systems. However, the variability and the uncertainty nature of the production and the consumption make the system more difficult to control. In fact, weather conditions influence on the production of renewable energy sources while occupancy influences on the power consumption. Therefore, the development of accurate short term forecasts are needed for a seamless integration of RES (e.g. photovoltaic system, wind turbine) together with the traditional electrical grid in MG systems. This paper presents a forecasting model for predicting the power production and consumption in MG systems together with the battery state of charge (SoC). A control strategy is then implemented to balance the Demand/Response by taking into account the forecasted and real-time values. Based on the data collected from a real MG system, simulation results are presented to show the effectiveness of power forecasting for MG control. © 2019 IEEE. |
| Author Keywords |
ARIMA model; control strategy; Demand/Response balance; IoT/Big-data platform; machine learning; micro-grid; power forecasting; state of charge |
