Residential Electricity Load Scenario Prediction Based on Transferable Flow Generation Model

Article Energy & Fuels

A deep generative model for probabilistic energy forecasting in power systems: normalizing flows

Jonathan Dumas et al.

Summary: The paper introduces a novel deep learning technique, normalizing flows, to produce accurate scenario-based probabilistic forecasts for power systems applications, addressing the challenges of renewable energy integration.

APPLIED ENERGY (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Short-Term Load Forecasting Using Channel and Temporal Attention Based Temporal Convolutional Network

Xianlun Tang et al.

Summary: Load forecasting is crucial for power system operation and planning. This paper proposes a short-term load forecasting model based on TCN and AM, which takes into account the non-linear relationship between meteorological factors and load. The model also utilizes MIC to select high-quality input variables and FCM combined with DTW to classify loads. Experimental results demonstrate that the proposed method significantly improves the accuracy and generalization capability of load forecasting compared to other models.

ELECTRIC POWER SYSTEMS RESEARCH (2022)

Add to Collection

Article Energy & Fuels

Probabilistic load forecasting considering temporal correlation: Online models for the prediction of households' electrical load

Julian Lemos-Vinasco et al.

Summary: This paper introduces two new modeling methods for producing multivariate probabilistic forecasts considering temporal correlation. Through a numerical experiment, it is found that the quantile-copula ensemble model outperforms the RLS-based models in predicting marginal distributions and capturing temporal correlation.

APPLIED ENERGY (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Load Forecasting Based on Weighted Grey Relational Degree and Improved ABC-SVM

Luo Ruxue et al.

Summary: This study proposes a short-term load forecasting method based on weighted grey relational degree and improved support vector machines with the artificial bee colony algorithm. Experimental results show that this method can effectively improve the accuracy of the forecasting model and simplify calculations, thus having research and practical value.

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Expression Transfer Using Flow-based Generative Models

Andrea Valenzuela et al.

Summary: This study explores the generation of deepfakes using flow-based methods for facial expression transfer, showcasing the feasibility of efficient expression transfer between different identities through latent vector operations. By utilizing a pre-trained model and small sets of images, the research demonstrates the potential of this approach and provides an evaluation based on image similarities and Action Units encoding.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021 (2021)

Add to Collection

Article Engineering, Electrical & Electronic