4.5 Article

A combination of novel hybrid deep learning model and quantile regression for short-term deterministic and probabilistic PV maximum power forecasting

Related references

Note: Only part of the references are listed.
Article Energy & Fuels

A compositive architecture coupling outlier correction, EWT, nonlinear Volterra multi-model fusion with multi-objective optimization for short-term wind speed forecasting

Ping Fang et al.

Summary: Short-term wind speed forecasting plays a positive role in power system dispatch and wind energy utilization. This study proposes an innovative approach that incorporates data preprocessing, multiple individual predictors, and Volterra multi-model fusion to improve accuracy and stability. Experimental results validate the effectiveness of the proposed method.

APPLIED ENERGY (2022)

Article Green & Sustainable Science & Technology

Multi-step solar irradiation prediction based on weather forecast and generative deep learning model

Yuan Gao et al.

Summary: With the rapid development of computer technology, deep learning models are increasingly used in solar radiation prediction. In this study, a deep generative model based on LSTM is developed for multi-step solar irradiation prediction. The results show that the generative model can effectively avoid error accumulation and the introduction of temperature forecast data from the previous day can significantly improve the accuracy of the prediction.

RENEWABLE ENERGY (2022)

Review Engineering, Multidisciplinary

A review of the hybrid artificial intelligence and optimization modelling of hydrological streamflow forecasting

Karim Sherif Mostafa Hassan Ibrahim et al.

Summary: Artificial Intelligence has been widely applied and researched in the field of hydrology, leading to the development of hybrid models with optimization techniques. This review paper categorizes and studies AI models and optimization techniques, summarizing their advantages and disadvantages. The focus of the research is the forecasting of streamflows, and future recommendations and conclusions are provided.

ALEXANDRIA ENGINEERING JOURNAL (2022)

Review Computer Science, Artificial Intelligence

Performance evaluation of outlier detection techniques in production timeseries: A systematic review and meta-analysis

Hamzeh Alimohammadi et al.

Summary: Time-series data is extensively collected and analyzed in various disciplines, with outliers causing uncertainties in interpretation results, making accurate and efficient outlier removal essential. This study applies 17 outlier detection techniques to oil and gas production data, with 15 being used for the first time. Evaluation based on various metrics reveals that eight unsupervised algorithms outperform the others, demonstrating the superior performance of ML-based techniques over statistical methods.

EXPERT SYSTEMS WITH APPLICATIONS (2022)

Article Computer Science, Artificial Intelligence

Efficient convolutional networks learning through irregular convolutional kernels

Weiyu Guo et al.

Summary: This work introduces a novel approach to achieve a lightweight model on low-power devices by reconstructing the structure of convolution kernels for efficient storage. Experimental results show that this approach significantly reduces the number of parameters and calculation costs while maintaining acceptable performance.

NEUROCOMPUTING (2022)

Proceedings Paper Materials Science, Multidisciplinary

Design and optimization of photovoltaic system with a week ahead power forecast using autoregressive artificial neural networks

R. K. Jarial et al.

Summary: This paper proposes an optimized design procedure for Photovoltaic system and a Autoregressive Neural Network model for predicting PV power output. The proposed model performs well and outperforms other time-series models according to the comparison results.

MATERIALS TODAY-PROCEEDINGS (2022)

Article Energy & Fuels

A temporal distributed hybrid deep learning model for day-ahead distributed PV power forecasting

Yinpeng Qu et al.

Summary: This paper presents a hybrid model based on Gated Recurrent Unit for forecasting distributed PV power generations. By utilizing locally historical PV power generation data, the model successfully predicts one-day-ahead solar power generation with improved accuracy.

APPLIED ENERGY (2021)

Article Thermodynamics

High dimensional very short-term solar power forecasting based on a data-driven heuristic method

Amir Rafati et al.

Summary: This paper introduces a univariate data-driven method to improve the accuracy of very short-term electrical solar power forecasting by defining new features to efficiently tackle the nonlinear characteristics of electrical solar power and using instance-based variable selection to identify the best relevant features, thus significantly enhancing the performance of very short-term solar power forecasting.

ENERGY (2021)

Article Computer Science, Artificial Intelligence

A hybrid quantum-classical neural network with deep residual learning

Yanying Liang et al.

Summary: Inspired by classical neural networks, a novel hybrid quantum-classical neural network with deep residual learning (Res-HQCNN) is proposed in this paper, which shows better performance in learning unknown unitary transformations and handling noisy data through experiments.

NEURAL NETWORKS (2021)

Article Physics, Multidisciplinary

A hybrid deep learning model with 1DCNN-LSTM-Attention networks for short-term traffic flow prediction

Ke Wang et al.

Summary: This paper proposed a short-term traffic flow prediction model based on the 1DCNN-LSTM network and attention mechanism, which combined the advantages of CNN spatial feature extraction and LSTM long-term memory, and showed better prediction performance under weather factors. Experimental results demonstrated that the model had faster convergence speed and higher prediction accuracy compared to traditional neural network models.

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (2021)

Article Green & Sustainable Science & Technology

Short-term self consumption PV plant power production forecasts based on hybrid CNN-LSTM, ConvLSTM models

Ali Agga et al.

Summary: Global electricity consumption has increased in the last century, leading to a growing importance of green energy sources like PV technology. This study introduces two hybrid models to predict power production for PV plants, showing higher accuracy compared to a standard LSTM model.

RENEWABLE ENERGY (2021)

Article Engineering, Electrical & Electronic

Data-Driven Copy-Paste Imputation for Energy Time Series

Moritz Weber et al.

Summary: Smart meters are crucial for the transition to smart grids, but missing values in energy time series pose challenges. This paper introduces a new Copy-Paste Imputation (CPI) method for energy time series, which outperforms benchmark methods by preserving total energy and utilizing matching patterns. The CPI method proves to be efficient in handling missing values with moderate run-time.

IEEE TRANSACTIONS ON SMART GRID (2021)

Article Green & Sustainable Science & Technology

Deep Concatenated Residual Network With Bidirectional LSTM for One-Hour-Ahead Wind Power Forecasting

Min-Seung Ko et al.

Summary: This paper introduces a deep residual network to enhance time-series forecasting models by connecting multi-level residual network and DenseNet, showing superior prediction accuracy on temperature and wind power datasets.

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY (2021)

Article Green & Sustainable Science & Technology

RSAM: Robust Self-Attention Based Multi-Horizon Model for Solar Irradiance Forecasting

Swati Sharda et al.

Summary: This study introduces a novel solar irradiance forecasting model utilizing self-attention mechanism in combination with multiple weather parameters and quantile regression to improve predictive accuracy and model robustness.

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY (2021)

Article Energy & Fuels

Long short term memory-convolutional neural network based deep hybrid approach for solar irradiance forecasting

Pratima Kumari et al.

Summary: The study introduces a new hybrid deep learning model, LSTM-CNN, for hourly GHI forecasting, trained with meteorological data from 23 locations in California and exhibiting high predictive accuracy under diverse climatic, seasonal, and sky conditions.

APPLIED ENERGY (2021)

Article Thermodynamics

Residential load forecasting based on LSTM fusing self-attention mechanism with pooling

Haixiang Zang et al.

Summary: This paper proposes a novel day-ahead residential load forecasting method based on feature engineering, pooling, and a hybrid deep learning model. Case studies on a practical dataset demonstrate the effectiveness and superiority of the proposed method.

ENERGY (2021)

Article Engineering, Mechanical

LSTM-based multi-layer self-attention method for remaining useful life estimation of mechanical systems

Jun Xia et al.

Summary: This paper proposes a new method based on LSTM and MLSA mechanism to improve the accuracy and computational efficiency of remaining useful life (RUL) estimation in mechanical systems. By designing multilayer MLSA mechanism and LSTM to extract and process degradation data features, the method is validated to have high computational efficiency, accuracy, and robustness in RUL estimation for aeroengines compared to other methods.

ENGINEERING FAILURE ANALYSIS (2021)

Article Green & Sustainable Science & Technology

PV-Net: An innovative deep learning approach for efficient forecasting of short-term photovoltaic energy production

Mohamed Abdel-Basset et al.

Summary: This study introduces a novel deep learning architecture called PV-Net for short-term forecasting of photovoltaic energy. The PV-Net utilizes Conv-GRU cells stacked in bidirectional blocks to efficiently extract features in PV power sequences. A real world case study shows the efficiency of PV-Net in terms of prediction precision and consistency.

JOURNAL OF CLEANER PRODUCTION (2021)

Article Energy & Fuels

Optimally configured Gated Recurrent Unit using Hyperband for the long-term forecasting of photovoltaic plant

Ameer Tamoor Khan et al.

Summary: The photovoltaic generation inherits the instability due to solar irradiation variability and non-availability, leading to grid management, planning, and operation issues. Researchers have proposed algorithms to forecast the power generation of photovoltaic plants, with the Hyperband Gated Recurrent Unit model achieving promising results by optimizing hyperparameters selection.

RENEWABLE ENERGY FOCUS (2021)

Article Energy & Fuels

A hybrid deep learning model for short-term PV power forecasting

Pengtao Li et al.

APPLIED ENERGY (2020)

Article Engineering, Electrical & Electronic

EnLSTM-WPEO: Short-Term Traffic Flow Prediction by Ensemble LSTM, NNCT Weight Integration, and Population Extremal Optimization

Feixiang Zhao et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2020)

Review Green & Sustainable Science & Technology

A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization

R. Ahmed et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2020)

Article Computer Science, Artificial Intelligence

Performance Evaluation of Probabilistic Methods Based on Bootstrap and Quantile Regression to Quantify PV Power Point Forecast Uncertainty

Yuxin Wen et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2020)

Article Green & Sustainable Science & Technology

An Adaptive Wind-Driven Optimization Algorithm for Extracting the Parameters of a Single-Diode PV Cell Model

Ibrahim Anwar Ibrahim et al.

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY (2020)

Review Green & Sustainable Science & Technology

A comprehensive review of hybrid models for solar radiation forecasting

Mawloud Guermoui et al.

JOURNAL OF CLEANER PRODUCTION (2020)

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)

Article Green & Sustainable Science & Technology

Photovoltaic power forecast using empirical models and artificial intelligence approaches for water pumping systems

Rim Ben Ammar et al.

RENEWABLE ENERGY (2020)

Proceedings Paper Energy & Fuels

Forecasting I-V Characteristic of PV Modules Considering Real Operating Conditions Using Numerical Method and Deep Learning

Nguyen Duc Tuyen et al.

2020 INTERNATIONAL CONFERENCE ON SMART GRIDS AND ENERGY SYSTEMS (SGES 2020) (2020)

Review Green & Sustainable Science & Technology

Review on forecasting of photovoltaic power generation based on machine learning and metaheuristic techniques

Muhammad Naveed Akhter et al.

IET RENEWABLE POWER GENERATION (2019)

Article Computer Science, Artificial Intelligence

Multiple convolutional neural networks for multivariate time series prediction

Kang Wang et al.

NEUROCOMPUTING (2019)

Article Automation & Control Systems

An Ensemble Framework for Day-Ahead Forecast of PV Output Power in Smart Grids

Muhammad Qamar Rene et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2019)

Article Computer Science, Information Systems

A Two-Layer Nonlinear Combination Method for Short-Term Wind Speed Prediction Based on ELM, ENN, and LSTM

Min-Rong Chen et al.

IEEE INTERNET OF THINGS JOURNAL (2019)

Article Thermodynamics

Integrated operation of renewable energy sources and water resources

Yu-Ching Tsai et al.

ENERGY CONVERSION AND MANAGEMENT (2018)

Review Green & Sustainable Science & Technology

Forecasting of photovoltaic power generation and model optimization: A review

Utpal Kumar Das et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2018)

Review Green & Sustainable Science & Technology

Review on probabilistic forecasting of photovoltaic power production and electricity consumption

D. W. van der Meer et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2018)

Article Green & Sustainable Science & Technology

An Efficient Forecasting-Optimization Scheme for the Intraday Unit Commitment Process Under Significant Wind and Solar Power

Samuel Cordova et al.

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY (2018)

Review Green & Sustainable Science & Technology

A review on time series forecasting techniques for building energy consumption

Chirag Deb et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2017)

Article Computer Science, Artificial Intelligence

Photovoltaic forecast based on hybrid PCA-LSSVM using dimensionality reducted data

M. Malvoni et al.

NEUROCOMPUTING (2016)

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)

Review Energy & Fuels

On recent advances in PV output power forecast

Muhammad Qamar Raza et al.

SOLAR ENERGY (2016)

Review Energy & Fuels

Review of photovoltaic power forecasting

J. Antonanzas et al.

SOLAR ENERGY (2016)

Article Computer Science, Interdisciplinary Applications

A simple more general boxplot method for identifying outliers

NC Schwertman et al.

COMPUTATIONAL STATISTICS & DATA ANALYSIS (2004)