Accepted author manuscript, 354 KB, PDF document
Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License
Final published version
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - State-of-the-art forecasting algorithms for microgrids
AU - Ma, Jie
AU - Ma, Xiandong
PY - 2017/10/26
Y1 - 2017/10/26
N2 - As a controllable subsystem integrating with the utility, a microgrid system consists of distributed energy sources, power conversion circuits, storage units and adjustable loads. Distributed energy sources employ non-polluted and sustainable resources such as wind and solar power in accordance with local terrain and climate to provide a reliable, consistent power supply for local customers. However, the electricity production in such a system is intermittent in nature, due to the time-varying weather conditions. Therefore, studies on accurate forecasting power generation and load demand are worthwhile in order to build a smart energy management system. The paper firstly reviews the forecasting algorithms for power supply side and load demand. The feasibly of the current control strategy is discussed. Finally, taking the wind turbine operational at Lancaster University campus as an example, results on power generation forecasting are presented by using a hybrid model combining Radial Basis Function and K-Means clustering. Development of new hybrid techniques aiming at improving model efficiency for online and real time forecasting will be one of the future research directions in this field.
AB - As a controllable subsystem integrating with the utility, a microgrid system consists of distributed energy sources, power conversion circuits, storage units and adjustable loads. Distributed energy sources employ non-polluted and sustainable resources such as wind and solar power in accordance with local terrain and climate to provide a reliable, consistent power supply for local customers. However, the electricity production in such a system is intermittent in nature, due to the time-varying weather conditions. Therefore, studies on accurate forecasting power generation and load demand are worthwhile in order to build a smart energy management system. The paper firstly reviews the forecasting algorithms for power supply side and load demand. The feasibly of the current control strategy is discussed. Finally, taking the wind turbine operational at Lancaster University campus as an example, results on power generation forecasting are presented by using a hybrid model combining Radial Basis Function and K-Means clustering. Development of new hybrid techniques aiming at improving model efficiency for online and real time forecasting will be one of the future research directions in this field.
U2 - 10.23919/IConAC.2017.8082049
DO - 10.23919/IConAC.2017.8082049
M3 - Conference contribution/Paper
SN - 9781509050406
BT - 23rd International Conference on Automation and Computing (ICAC),2017
PB - IEEE
ER -