Artificial intelligence and digital twins in power systems: Trends, synergies and opportunities

Digital Twin, Journal Year: 2023, Volume and Issue: 2, P. 11 - 11

Published: March 13, 2023

Artificial Intelligence (AI) promises solutions to the challenges raised by digitalization of power grids and their assets. Decision-making, forecasting even operational optimization assets are just some that AI algorithms can provide operators, utilities vendors. Nevertheless, barriers such as access quality datasets, interpretability, repeatability, availability computational resources currently limit extent practical implementations. At same time, Digital Twins (DTs) foreseen platforms overcome these barriers, also a new environment for development enhanced more intelligent applications. In this manuscript, we review published literature determine existing capabilities implementation in systems, classify AI-based applications based on time scale reveal temporal sensitivity. Furthermore, DT-based technologies discussed, identifying potentials tackle current limitations real-world well exploring synergies between DTs AI. By combining DT, outline multiple prospective use cases AI-enhanced grid asset DTs. Our identifies combination leverages with potential fundamentally change aspects industry.

Language: Английский

---

Day-ahead solar photovoltaic energy forecasting based on weather data using LSTM networks: a comparative study for photovoltaic (PV) panels in Turkey

Electrical Engineering, Journal Year: 2023, Volume and Issue: 105(5), P. 3329 - 3345

Published: June 19, 2023

Language: Английский

---

Online cross session electromyographic hand gesture recognition using deep learning and transfer learning

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 127, P. 107251 - 107251

Published: Oct. 9, 2023

Language: Английский

---

A Novel Dual-Channel Temporal Convolutional Network for Photovoltaic Power Forecasting

Energies, Journal Year: 2024, Volume and Issue: 17(3), P. 698 - 698

Published: Feb. 1, 2024

A large proportion of photovoltaic (PV) power generation is connected to the grid, and its volatility stochasticity have significant impacts on system. Accurate PV forecasting great significance in optimizing safe operation grid market transactions. In this paper, a novel dual-channel method based temporal convolutional network (TCN) proposed. The deeply integrates station feature data with model computing mechanism through architecture; utilizes combination multihead attention (MHA) TCN extract multidimensional spatio-temporal features between other meteorological variables power; single fully constraints sequence elements. weighted fusion ultimately yields ideal results. experimental study are from 26.52 kW plant central Australia. experiments were carried out over seven different input window widths, two models that currently show superior performance within field forecasting: neural (CNN), combined long short-term memory (CNN_LSTM), used as baseline models. results proposed both obtained best 1-day width, while exhibited compared model. It also shows designing architectures integrate has research potential forecasting.

Language: Английский

---

Solar irradiance time series forecasting using auto-regressive and extreme learning methods: Influence of transfer learning and clustering

Applied Energy, Journal Year: 2024, Volume and Issue: 365, P. 123215 - 123215

Published: April 17, 2024

Language: Английский

---