Day‐ahead renewable scenario forecasts based on generative adversarial networks

Abstract

Summary With the increasing penetration of renewable resources such as wind and solar, especially in terms of large‐scale integration, the operation and planning of power systems are faced with great risks due to the inherent stochasticity of natural resources. Although this uncertainty can be anticipated, the timing, magnitude, and duration of fluctuations cannot be predicted accurately. In addition, the outputs of renewable power sources are correlated in space and time, and this brings further challenges for predicting the characteristics of their future behavior. To address these issues, this paper describes an unsupervised distribution learning method for renewable scenario forecasts that considers spatiotemporal correlation based on generative adversarial network (GAN), which has been shown to generate realistic time series for stochastic processes. We first utilize an improved GAN to learn unknown data distributions and model the dynamic processes of renewable resources. We then generate a large number of forecasted scenarios using stochastic constrained optimization. For validation, we use power generation data from the National Renewable Energy Laboratory wind and solar integration datasets. The simulation results show that the generated trajectories not only reflect the future power generation dynamics, but also correctly capture the temporal, spatial, and fluctuant characteristics of the real power generation processes. The experimental comparisons verify the superiority of the proposed method and indicate that it can reduce at least 50% of the training iterations of the generative model for scenario forecasts.

A Review of Solar Power Scenario Generation Methods with Focus on Weather Classifications, Temporal Horizons, and Deep Generative Models

“…Non-parametric forecasting-based methods are completely data-driven and independent of any form of distribution assumption. Most methods are based on DGMs, which have gained increasing popularity in recent years for SPS generation [16,20,26,[78][79][80][81][82][83][84][85][86][87][88][89][90][91][92]. DGMs are completely assumption-free and generate new synthetic data that highly resemble the training samples.…”

Deep Learning for Time Series Forecasting: Advances and Open Problems

“…Year Application [159] 2018 Stock market [160] 2019 Traffic forecasting [154] 2019 Lorenz/Mackey-Glass/Internet Traffic data [161] 2019 Medicine expenditure [162] 2019 Electricity load [163] 2020 Stock price [164] 2020 Long-term benchmark data sets (see Section 6.2) [165] 2020 Soil temperature [166] 2021 Stock market/Energy production/EEG/Air quality [156] 2021 Internet Traffic data [167] 2021 Store Item Demand/Internet Traffic/Meteorological data [168] 2021 Wind power/Solar power [144] 2021 Energy consumption [169] 2021 Electricity load [170] 2022…”

Deep reinforcement learning for real-time economic energy management of microgrid system considering uncertainties

“…In the existing model-based research work, wind speed and light or their errors are usually assumed to follow known probability distributions (Liang and Tang, 2020;Khosravi et al, 2022;Malik et al, 2022) and are used to model wind power and PV output to obtain renewable energy output data. However, the modeling process for these probability distribution models is complex, the parameters are difficult to identify, and a large sample of actual operational data is required, which is very time consuming (Jiang et al, 2021). Furthermore, the actual system operating data do not strictly obey these probability distribution functions, so we use the historical data of real power systems to learn the transition probability.…”