Day-ahead scenario generation of renewable power plays an important role in short-term power system operations due to considerable output uncertainty included. In this paper, a deep renewable scenario generation model using style-based generative adversarial networks followed by a sequence encoder network, is developed to generate accurate and reliable day-ahead scenarios directly from historical data through different-level scenario style controlling and mixing, thus achieving better characterization of renewable spatial-temporal dynamics. Meanwhile, the integration of meteorological information serving as conditions enables our model to precisely capture the complex diurnal pattern and seasonality difference of renewable power. From wind and photovoltaic power perspectives, the effectiveness of the proposed model is validated on two real-world datasets reflecting region aggregation level and distributed power station level respectively. Numerical results demonstrate the superiority of model performance through both the statistical and power system scheduling analysis, compared to three benchmarks.
Considering nonstatistical uncertainties and/or insufficient historical data in security return forecasts, fuzzy set theory has been applied in the past decades to build portfolio selection models. Meanwhile, various risk measurements such as variance, entropy, and Value-at-Risk have been proposed in fuzzy environments to evaluate investment risks from different perspectives. Sharpe ratio, also known as the reward-to-variability ratio, which measures the risk premium per unit of the nonsystematic risk (asset deviation), has received great attention in modern portfolio theory. In this study, the Sharpe ratio in fuzzy environments is introduced, whereafter, a fuzzy Value-at-Risk ratio is proposed. Compared with Sharpe ratio, Value-at-Risk ratio is an index with dimensional knowledge that reflects the risk premium per unit of the systematic risk (the greatest loss under a given confidence level). On the basis of the two ratios, a multi-objective model is built to evaluate their joint impact on portfolio selection. Then, the proposed model is solved by a fuzzy simulation based multi-objective particle swarm optimization algorithm, where the global best of each iteration is determined by an improved dominance times based method. Finally, the algorithm superiority is justified via comparing with existing solvers on benchmark problems, and the model effectiveness is exemplified by using three case studies on portfolio selection.
9 August 2021 in International Journal of Machine Learning and Cybernetics