TY - JOUR
T1 - WindGMMN
T2 - Scenario Forecasting for Wind Power Using Generative Moment Matching Networks
AU - Liao, Wenlong
AU - Yang, Zhe
AU - Chen, Xinxin
AU - Li, Yaqi
PY - 2022/10
Y1 - 2022/10
N2 - With the increasing penetration of wind power generation, the fluctuating and intermittent behavior of wind power poses huge challenges to the operation and planning of distribution networks. A popular way to mitigate these challenges is to provide a group of possible wind power forecasting scenarios instead of depending on deterministic point forecasting values, so that system operators can consider the uncertainties. This letter proposes a novel WindGMMN method for wind power scenario forecasting, in which necessary modifications are made on the generative moment matching network (GMMN), and an optimization strategy is designed to find a series of wind power scenarios with similar shapes, probability distributions, and temporal correlations as potential scenarios. Simulations and analyses were performed on a public dataset with 2190 wind power generation curves and their corresponding meteorological features. The results show that the proposed WindGMMN outperforms popular baselines (e.g., variational auto-encoders and generative adversarial networks) for scenario forecasting of wind power, without any restrictions on the time horizon (e.g., times ranging from 10 min to 24 h).
AB - With the increasing penetration of wind power generation, the fluctuating and intermittent behavior of wind power poses huge challenges to the operation and planning of distribution networks. A popular way to mitigate these challenges is to provide a group of possible wind power forecasting scenarios instead of depending on deterministic point forecasting values, so that system operators can consider the uncertainties. This letter proposes a novel WindGMMN method for wind power scenario forecasting, in which necessary modifications are made on the generative moment matching network (GMMN), and an optimization strategy is designed to find a series of wind power scenarios with similar shapes, probability distributions, and temporal correlations as potential scenarios. Simulations and analyses were performed on a public dataset with 2190 wind power generation curves and their corresponding meteorological features. The results show that the proposed WindGMMN outperforms popular baselines (e.g., variational auto-encoders and generative adversarial networks) for scenario forecasting of wind power, without any restrictions on the time horizon (e.g., times ranging from 10 min to 24 h).
KW - Deep learning
KW - generative moment matching network (GMMN)
KW - machine learning
KW - scenario forecasts
KW - wind power
UR - http://www.scopus.com/inward/record.url?scp=85130518199&partnerID=8YFLogxK
U2 - 10.1109/TAI.2021.3128368
DO - 10.1109/TAI.2021.3128368
M3 - Journal article
SN - 2691-4581
VL - 3
SP - 843
EP - 850
JO - IEEE Transactions on Artificial Intelligence
JF - IEEE Transactions on Artificial Intelligence
IS - 5
ER -