hr Hybrid classification-regression metric for the prediction of constraint violations in distribution networks

Article Energy & Fuels

Prediction of the effects of climate change on hydroelectric generation, electricity demand, and emissions of greenhouse gases under climatic scenarios and optimized ANN model

Li-Na Guo et al.

Summary: This study aims to manage the gap between energy demand and supply by predicting hydropower production, energy demand, and greenhouse gas emissions. The results show a decrease in hydroelectric generation and an increase in energy demand in the future, leading to an increased gap between demand and supply.

ENERGY REPORTS (2021)

添加到收藏夹

Article Energy & Fuels

Advances in the Application of Machine Learning Techniques for Power System Analytics: A Survey

Seyed Mahdi Miraftabzadeh et al.

Summary: With recent advances in computing technologies and the increasing availability of large amounts of data in smart grids and smart cities, new research opportunities are emerging for applying Machine Learning to improve the observability and efficiency of modern power grids. A systematic review of state-of-the-art studies implementing ML techniques in power systems reveals that ML algorithms can handle massive quantities of data with high dimensionality and hybrid models generally show better performances than single ML-based models.

ENERGIES (2021)

添加到收藏夹

Article Energy & Fuels

Adaptive Power Flow Prediction Based on Machine Learning

Jingyeong Park et al.

Summary: Power flow analysis is an essential method in the planning and operation of the power grid. This paper proposes an alternative method for distribution systems based on available parameters at terminal nodes, and develops two machine learning schemes for high-voltage and low-voltage systems. The performance of the models is verified through numerical simulations and compared with another power flow scheme for distribution systems.

ENERGIES (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Physics-Guided Deep Neural Networks for Power Flow Analysis

Xinyue Hu et al.

Summary: The paper proposes a physics-guided neural network approach to solve the PF problem with an auxiliary task to rebuild the PF model. By encoding different granularity of Kirchhoff's laws and system topology into the rebuilt PF model, the neural network-based PF solver is regularized by the auxiliary task and constrained by the physical laws. Simulation results demonstrate that the physics-guided neural network methods achieve better performance and generalizability compared to existing unconstrained data-driven approaches. Additionally, it is shown that the weight matrices of the proposed neural networks embody power system physics by showing their similarities with the bus admittance matrices.

IEEE TRANSACTIONS ON POWER SYSTEMS (2021)

添加到收藏夹

Article Biotechnology & Applied Microbiology