☆ 4.7 Article

A theory-guided deep-learning method for predicting power generation of multi-region photovoltaic plants

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2023)

Related references

Note: Only part of the references are listed.

Article Thermodynamics

A knowledge-enhanced graph-based temporal-spatial network for natural gas consumption prediction

Jian Du et al.

Summary: Accurate prediction of natural gas consumption is crucial for long-distance pipeline system production and transportation planning, especially in the current political situation. Existing prediction methods lack consideration of spatial correlations and domain knowledge. This study proposes a novel deep learning prediction method (KE-GB-TSN) that integrates domain knowledge into association graph construction and captures temporal-spatial features, leading to more accurate and efficient predicted results compared to advanced models.

ENERGY (2023)

Add to Collection

Article Thermodynamics

A hybrid deep learning framework for predicting daily natural gas consumption

Jian Du et al.

Summary: This paper proposes a novel method that addresses the deficiency of conventional time series prediction for natural gas consumption by designing a hybrid deep learning framework to extract comprehensive information. The proposed model enables accurate and efficient prediction of natural gas consumption by capturing static and dynamic information and integrating long-term dependency patterns.

ENERGY (2022)

Add to Collection

Article Automation & Control Systems

Adaptive transfer learning-based multiscale feature fused deep convolutional neural network for EEG MI multiclassification in brain-computer interface

Arunabha M. Roy

Summary: This study introduces an efficient transfer learning-based multi-scale feature fused convolutional neural network for classification of motor imagery, which can capture distinguishable features from different EEG frequency bands at various convolutional scales.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2022)

Add to Collection

Article Automation & Control Systems

A new approach to dominant motion pattern recognition at the macroscopic crowd level

Franjo Matkovic et al.

Summary: This paper introduces a novel method for automatic analysis of large-scale crowd behavior by recognizing dominant motion patterns. Inspired by quantum mechanics, the method combines particle trajectories and wave functions to achieve recognition of dominant motion patterns.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2022)

Add to Collection

Article Green & Sustainable Science & Technology

Uncovering wind power forecasting uncertainty sources and their the whole chain

Jie Yan et al.

Summary: This paper presents a qualitative review on wind power forecasting uncertainty, providing strategies for mitigating different uncertainty sources and discussing the importance of uncertainty validation.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2022)

Add to Collection

Article Green & Sustainable Science & Technology

Integrated design of photovoltaic power generation plant with pumped hydro storage system and irrigation facility at the Uhuelem-Amoncha African community

Uchenna Godswill Onu et al.

Summary: This paper presents an integrated design for photovoltaic power generation with a pumped hydro storage system, which can be used for irrigation and community utilization. By utilizing natural water sources and a photovoltaic plant, reliable power supply and water sources can be provided, improving the economic sustainability of rural grids.

RENEWABLE ENERGY (2022)

Add to Collection

Article Multidisciplinary Sciences

Linear programing formulation of a high temporal and technological resolution integrated energy system model for the energy transition

Manuel Sanchez Dieguez et al.

Summary: This study proposes a new method to address the challenges of energy transition by representing different activities in the energy system at different temporal scales. The model can effectively simulate the feasibility of the system by describing the flexibility of different sectors in high resolution.

METHODSX (2022)

Add to Collection

Article Thermodynamics

A novel adaptive discrete grey model with time-varying parameters for long-term photovoltaic power generation forecasting

Song Ding et al.

Summary: The paper introduces a new discrete grey model with time-varying parameters to accurately predict long-term photovoltaic power generation, addressing the issue of overfitting and large forecasting deviations commonly associated with artificial neuron networks when dealing with long-term datasets.

ENERGY CONVERSION AND MANAGEMENT (2021)

Add to Collection

Article Thermodynamics

Day-ahead hourly photovoltaic power forecasting using attention-based CNN-LSTM neural network embedded with multiple relevant and target variables prediction pattern

Jiaqi Qu et al.

Summary: Accurate forecasting of photovoltaic power is crucial for smart grid systems, with this study proposing an attention based neural network model to capture short-term and long-term temporal modes and achieve day-ahead hourly predictions with better accuracy than traditional methods. The model outperforms other forecasting methods and provides insights on improving accuracy by analyzing important parameters.

ENERGY (2021)

Add to Collection

Article Energy & Fuels

1.6 Million transactions replicate distributed PV market slowdown by COVID-19 lockdown

Haoran Zhang et al.

Summary: The COVID-19 pandemic may have negative impacts on the photovoltaic industry, especially in the distributed market. Research suggests that a two-month lockdown period is considered a high-risk threshold, exceeding which will significantly reduce market value and emission reduction capacity. Therefore, comprehensive incentive strategies can help mitigate the risks of PV deployment slowdown due to COVID-19 lockdowns.

APPLIED ENERGY (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

A federated learning system with enhanced feature extraction for human activity recognition

Zhiwen Xiao et al.

Summary: This paper presents a federated learning system for human activity recognition, HARFLS, which includes a perceptive extraction network (PEN) that extracts features through a feature network and a relation network. Compared to other systems, it achieves higher recognition accuracy, especially on the WISDM and PAMAP2 datasets.

KNOWLEDGE-BASED SYSTEMS (2021)

Add to Collection

Article Thermodynamics

Deep learning based forecasting of photovoltaic power generation by incorporating domain knowledge

Xing Luo et al.

Summary: This study introduces a deep learning framework for accurate PVPG forecasting, overcoming the limitations of traditional machine learning algorithms. Experimental results demonstrate that the PC-LSTM model has stronger forecasting capability and higher accuracy.

ENERGY (2021)

Add to Collection

Article Engineering, Civil

Coupling a hybrid CNN-LSTM deep learning model with a Boundary Corrected Maximal Overlap Discrete Wavelet Transform for multiscale Lake water level forecasting

Rahim Barzegar et al.

Summary: This study demonstrated the importance of accurate lake water level forecasting models for various applications. By combining BC-MODWT data preprocessing with a hybrid CNN-LSTM deep learning model, improved accuracy in Lake Michigan and Lake Ontario water level predictions was achieved, surpassing traditional machine learning models. The proposed BC-MODWT-CNN-LSTM model proved to be a potentially useful approach for enhancing the accuracy of lake water level forecasts.

JOURNAL OF HYDROLOGY (2021)

Add to Collection

Article Green & Sustainable Science & Technology

A regression unsupervised incremental learning algorithm for solar irradiance prediction

Boon Keat Puah et al.

Summary: Solar irradiance intensity directly affects solar power generation, making accurate forecasting essential for energy management systems. This paper introduces a novel artificial intelligence algorithm, RE-SOINN, for real-time and adaptive solar irradiance forecasting, showing higher accuracy compared to other models in fluctuating conditions.

RENEWABLE ENERGY (2021)

Add to Collection

Article Thermodynamics

A point prediction method based automatic machine learning for day-ahead power output of multi-region photovoltaic plants

Wei Zhao et al.

Summary: This paper presents a combined method for day-ahead solar power generation (SPG) prediction of multi-region photovoltaic (PV) plants, which integrates automatic machine learning, improved genetic algorithm, and SPG physical model. The method is evaluated with real data from multi-region PV plants in Hokkaido, demonstrating acceptable accuracy and outperforming several baselines and other methods.

ENERGY (2021)

Add to Collection

Article Thermodynamics

Techno-economic assessment of photovoltaic power generation mounted on cooling towers

Lingfei Qi et al.

Summary: The study evaluated the economic and power generation potential of deploying photovoltaic systems on cooling towers in Mainland China, showing that this deployment strategy has good technical and economic performance.

ENERGY CONVERSION AND MANAGEMENT (2021)

Add to Collection

Review Thermodynamics

A review on global solar radiation prediction with machine learning models in a comprehensive perspective

Yong Zhou et al.

Summary: This paper comprehensively reviews important aspects of machine-learning models in predicting global solar radiation, including input parameters and feature selection methods. It discusses different sources of input parameters and feature selection methods, and identifies seven classes of machine-learning models. Finally, it discusses the current and future research status.

ENERGY CONVERSION AND MANAGEMENT (2021)

Add to Collection

Article Engineering, Multidisciplinary

Fault detection of wind turbine based on SCADA data analysis using CNN and LSTM with attention mechanism

Ling Xiang et al.

Summary: A new method for fault detection of wind turbines is proposed in this paper, which combines CNN and LSTM networks trained on SCADA data to enhance accuracy and predictive effectiveness.

MEASUREMENT (2021)

Add to Collection

Article Energy & Fuels

Machine learning enabled reduced-order scenario generation for stochastic analysis of solar power forecasts

S. Bhavsar et al.

Summary: This work presents a novel and efficient method to generate statistically accurate scenarios from probabilistic forecasts and reduce the number of scenarios using unsupervised machine learning, while preserving the statistical properties of the original set. The approach yields statistically equivalent characteristics as a full set with a substantially reduced cardinality and preserves the temporal correlation in time-series data.

APPLIED ENERGY (2021)

Add to Collection

Article Energy & Fuels

A city-scale estimation of rooftop solar photovoltaic potential based on deep learning

Teng Zhong et al.

Summary: A generic framework for estimating rooftop solar PV potential on a city-scale using publicly available high-resolution satellite images is proposed in this study. By developing a deep learning-based method for rooftop extraction and a spatial optimization sampling strategy, the labor cost for preparing the dataset and training the model has been significantly reduced while improving the model's robustness.

APPLIED ENERGY (2021)

Add to Collection

Article Construction & Building Technology

Predicting hourly heating load in a district heating system based on a hybrid CNN-LSTM model

Jiancai Song et al.

Summary: Predicting heating load accurately is crucial for smart heating systems. This study introduces a novel estimation model based on spatiotemporal hybrid convolution neural network long-short term memory (CNN-LSTM), which integrates the strengths of CNN and LSTM to achieve higher prediction accuracy for heating load, providing a more reasonable and precise prediction in a dynamic environment.

ENERGY AND BUILDINGS (2021)

Add to Collection

Article Computer Science, Information Systems

RTFN: A robust temporal feature network for time series classification

Zhiwen Xiao et al.

Summary: Time series data contains both local and global patterns, but existing feature networks focus on local features and neglect the relationships among them. Therefore, a novel RTFN method is proposed for feature extraction in time series, consisting of TFN and LSTMaN. Experimental results show that the RTFN-based structures achieve excellent performance on multiple datasets.

INFORMATION SCIENCES (2021)

Add to Collection

Article Green & Sustainable Science & Technology

Hybrid deep neural model for hourly solar irradiance forecasting

Xiaoqiao Huang et al.

Summary: Due to the integration of photovoltaic solar systems into power networks, accurate prediction of solar irradiance is crucial for electric energy planning and management. This study proposes a novel multivariate hybrid deep neural model named WPD-CNN-LSTM-MLP for 1-hour ahead solar irradiance forecasting. The model combines WPD, CNN, LSTM, and MLP with multi-variable inputs, achieving more accurate results compared to traditional models.

RENEWABLE ENERGY (2021)

Add to Collection

Article Environmental Sciences

Spatiotemporal variations and regional differences in air temperature in the permafrost regions in the Northern Hemisphere during 1980-2018

Guojie Hu et al.

Summary: This study analyzed the variations and regional differences in air temperature from 1980 to 2018, showing that the warming rate in permafrost regions was higher than the global average, with significant differences between high latitude, transitional, and high altitude permafrost regions. Additionally, the results indicated different trends in freezing and thawing degree-days across different permafrost zones.

SCIENCE OF THE TOTAL ENVIRONMENT (2021)

Add to Collection

Article Energy & Fuels

New York State's 100% renewable electricity transition planning under uncertainty using a data-driven multistage adaptive robust optimization approach with machine-learning

Ning Zhao et al.

Summary: Power system decarbonization is crucial for combating climate change, and addressing systems uncertainties is essential for designing robust renewable transition pathways. A data-driven multistage adaptive robust optimization (MARO) framework is proposed in this study to handle renewable transition under uncertainty, using machine learning techniques to construct data-driven uncertainty sets. The results show higher total renewable electricity transition costs under uncertainty compared to deterministic planning, but utilizing data-driven uncertainty sets can lower the costs.

ADVANCES IN APPLIED ENERGY (2021)

Add to Collection

Article Energy & Fuels

Theory-guided deep-learning for electrical load forecasting (TgDLF) via ensemble long short-term memory

Yuntian Chen et al.

Summary: The study introduces a theory-guided deep-learning load forecasting model, TgDLF, which predicts future load through load ratio decomposition and data-driven models, improving accuracy and robustness.

ADVANCES IN APPLIED ENERGY (2021)

Add to Collection

Article Energy & Fuels

Measuring accuracy and computational capacity trade-offs in an hourly integrated energy system model

Amirhossein Fattahi et al.

Summary: Improving energy system modeling capabilities can directly affect the quality of applied studies, but some trade-offs are necessary due to computational constraints. This paper demonstrates the trade-offs resulting from modifying the resolution of modeling capabilities, showing the impact on computational time and various energy system modeling indicators. Increasing resolution in modeling flexible options can significantly improve results, while neglecting infrastructure representation may underestimate the objective function.

ADVANCES IN APPLIED ENERGY (2021)

Add to Collection

Article Energy & Fuels

Urban power load profiles under ageing transition integrated with future EVs charging

Haoran Zhang et al.

Summary: Understanding the fine-grained changes in electricity profile caused by ageing transition is crucial for managing future threats in grid flexibility. Research on hourly-basis knowledge gaps exists due to challenges in microanalysis of user behavior. Through the analysis of billions of users' data, it was found that population ageing leads to a decrease in participation in high electricity-density activities, resulting in a 14% difference between peak charging load and valley, and will significantly change the magnitude and shape of future dynamic load profiles. It is suggested to have comprehensive and quantitative management for PVs development and the smart charging market to deal with potential challenges caused by ageing.

ADVANCES IN APPLIED ENERGY (2021)

Add to Collection

Article Green & Sustainable Science & Technology

Long short-term memory recurrent neural network for modeling temporal patterns in long-term power forecasting for solar PV facilities: Case study of South Korea

Yoonhwa Jung et al.

JOURNAL OF CLEANER PRODUCTION (2020)

Add to Collection

Article Energy & Fuels

Time series prediction for output of multi-region solar power plants

Jianqin Zheng et al.

APPLIED ENERGY (2020)

Add to Collection

Editorial Material Energy & Fuels

Solar energy integration in buildings

Jinqing Peng et al.

APPLIED ENERGY (2020)

Add to Collection

Article Green & Sustainable Science & Technology

An improved moth-flame optimization algorithm for support vector machine prediction of photovoltaic power generation

Guo-Qian Lin et al.

JOURNAL OF CLEANER PRODUCTION (2020)

Add to Collection

Article Engineering, Civil

Deep learning of subsurface flow via theory-guided neural network

Nanzhe Wang et al.

JOURNAL OF HYDROLOGY (2020)

Add to Collection

Article Green & Sustainable Science & Technology

Time series forecasting of solar power generation for large-scale photovoltaic plants

Hussein Sharadga et al.

RENEWABLE ENERGY (2020)

Add to Collection

Article Energy & Fuels

Climate change impact of integrating a solar microgrid system into the Swedish electricity grid

Asterios Papageorgiou et al.

APPLIED ENERGY (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Short-term photovoltaic power generation forecasting based on random forest feature selection and CEEMD: A case study

Dongxiao Niu et al.

APPLIED SOFT COMPUTING (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Interpretable spatio-temporal attention LSTM model for flood forecasting

Yukai Ding et al.

NEUROCOMPUTING (2020)

Add to Collection

Article Thermodynamics

A minutely solar irradiance forecasting method based on real-time sky image-irradiance mapping model

Fei Wang et al.

ENERGY CONVERSION AND MANAGEMENT (2020)

Add to Collection

Article Energy & Fuels

State-of-the-art power electronics systems for solar-to-grid integration

Venkata R. Vakacharla et al.

SOLAR ENERGY (2020)

Add to Collection

Article Green & Sustainable Science & Technology

Potential of unsubsidized distributed solar PV to replace coal-fired power plants, and profits classification in Chinese cities

Ying Yang et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2020)

Add to Collection

Article Green & Sustainable Science & Technology

Short term solar irradiance forecasting via a novel evolutionary multi-model framework and performance assessment for sites with no solar irradiance data

Manal Marzouq et al.

RENEWABLE ENERGY (2020)

Add to Collection

Article Thermodynamics

Solar irradiance forecasting based on direct explainable neural network

Huaizhi Wang et al.

ENERGY CONVERSION AND MANAGEMENT (2020)

Add to Collection

Article Chemistry, Physical

Solar-driven integrated energy systems: State of the art and challenges

Yuhan Wu et al.

JOURNAL OF POWER SOURCES (2020)

Add to Collection

Article Green & Sustainable Science & Technology

Constructing statutory energy goal compliant wind and solar PV infrastructure pathways

Austin Thomas et al.

RENEWABLE ENERGY (2020)

Add to Collection

Article Green & Sustainable Science & Technology

Hourly forecasting of solar irradiance based on CEEMDAN and multi-strategy CNN-LSTM neural networks

Bixuan Gao et al.

RENEWABLE ENERGY (2020)

Add to Collection

Article Multidisciplinary Sciences

Using Existing Infrastructure to Realize Low-Cost and Flexible Photovoltaic Power Generation in Areas with High-Power Demand in China

Mingkun Jiang et al.

ISCIENCE (2020)

Add to Collection

Article Green & Sustainable Science & Technology

Short-term global horizontal irradiance forecasting based on a hybrid CNN-LSTM model with spatiotemporal correlations

Haixiang Zang et al.

RENEWABLE ENERGY (2020)

Add to Collection

Article Green & Sustainable Science & Technology

Automatic hourly solar forecasting using machine learning models

Gokhan Mert Yagli et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2019)

Add to Collection

Article Thermodynamics

Development of Photovoltaic abnormal condition detection system using combined regression and Support Vector Machine

Fauzan Hanif Jufri et al.

ENERGY (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Temporal pattern attention for multivariate time series forecasting

Shun-Yao Shih et al.

MACHINE LEARNING (2019)

Add to Collection

Article Thermodynamics

Production capacity analysis and energy saving of complex chemical processes using LSTM based on attention mechanism

Yongming Han et al.

APPLIED THERMAL ENGINEERING (2019)

Add to Collection

Article Green & Sustainable Science & Technology

Renewable energy prediction: A novel short-term prediction model of photovoltaic output power

Ling-Ling Li et al.

JOURNAL OF CLEANER PRODUCTION (2019)

Add to Collection

Article Energy & Fuels

City-level analysis of subsidy-free solar photovoltaic electricity price, profits and grid parity in China

Jinyue Yan et al.

NATURE ENERGY (2019)

Add to Collection

Article Thermodynamics

Photovoltaic power forecasting based LSTM-Convolutional Network

Kejun Wang et al.

ENERGY (2019)

Add to Collection

Proceedings Paper Energy & Fuels

Performance of a Hybrid Solar Photovoltaic - Air Source Heat Pump System with Energy Storage

Yuexia Lv et al.

INNOVATIVE SOLUTIONS FOR ENERGY TRANSITIONS (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Theory-Guided Data Science: A New Paradigm for Scientific Discovery from Data

Anuj Karpatne et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2017)

Add to Collection

Article Energy & Fuels

Forecasting the daily power output of a grid-connected photovoltaic system based on multivariate adaptive regression splines

Yanting Li et al.

APPLIED ENERGY (2016)

Add to Collection

Article Green & Sustainable Science & Technology

One-day-ahead daily power forecasting of photovoltaic systems based on partial functional linear regression models

Guochang Wang et al.

RENEWABLE ENERGY (2016)

Add to Collection

Article Green & Sustainable Science & Technology

Compressive Spatio-Temporal Forecasting of Meteorological Quantities and Photovoltaic Power

Akin Tascikaraoglu et al.

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY (2016)

Add to Collection

Article Green & Sustainable Science & Technology

Development of statistical time series models for solar power prediction

V. Prema et al.

RENEWABLE ENERGY (2015)

Add to Collection

Review Multidisciplinary Sciences

Machine learning: Trends, perspectives, and prospects

M. I. Jordan et al.

SCIENCE (2015)

Add to Collection

Article Green & Sustainable Science & Technology

An ARMAX model for forecasting the power output of a grid connected photovoltaic system

Yanting Li et al.

RENEWABLE ENERGY (2014)

Add to Collection

Article Green & Sustainable Science & Technology

Short-term solar power prediction using a support vector machine

Jianwu Zeng et al.

RENEWABLE ENERGY (2013)

Add to Collection

Article Energy & Fuels

Short-mid-term solar power prediction by using artificial neural networks

Ercan Izgi et al.

SOLAR ENERGY (2012)

Add to Collection

Article Energy & Fuels

Predicting solar radiation at high resolutions: A comparison of time series forecasts

Gordon Reikard

SOLAR ENERGY (2009)

Add to Collection

© Peeref 2019-2024. All rights reserved.