☆ 4.7 Article

A composite framework for photovoltaic day-ahead power prediction based on dual clustering of dynamic time warping distance and deep autoencoder

RENEWABLE ENERGY (2022)

Related references

Note: Only part of the references are listed.

Article Optics

A robust auto encoder-gated recurrent unit (AE-GRU) based deep learning approach for short term solar power forecasting

Amit Rai et al.

Summary: The increasing presence of solar power plants demonstrates their potential as a key renewable energy resource to meet the energy demands of communities. This study introduces a hybrid deep learning approach based on sequence to sequence auto-encoder (AE) and Gated Recurrent Unit (GRU), which outperforms other deep learning models in solar power forecasting.

OPTIK (2022)

Add to Collection

Article Thermodynamics

Feasibility investigation on using silver nanorods in energy saving windows for light/heat decoupling

Jihong Pu et al.

Summary: Metallic nanoparticles, such as silver nanorods, with localized surface plasmon resonance can efficiently absorb solar energy in a specific range. This study investigated the optical properties of silver nanorods using the Discrete Dipole Approximation (DDA) approach and studied the spectral response of silver nanorod/polymer nanocomposites using a Monte Carlo method. Optimal hybridizations of silver nanorods were proposed to achieve high luminous transmittance and thermal radiation insulation. The findings suggest that decreasing the diameter of silver nanorods can improve radiation shielding performance and luminous transmittance, while insignificant changes occur when the diameter decreases further. The proposed silver nanorod/polymer nanocomposites show promise in achieving light/heat splitting with high luminous transmittance and solar radiation blocking.

ENERGY (2022)

Add to Collection

Article Green & Sustainable Science & Technology

Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction

David Markovics et al.

Summary: This study compares 24 machine learning models for deterministic day-ahead power forecasting and finds that kernel ridge regression and multilayer perceptron are the most accurate models. Supplementary inputs like Sun position angles and irradiance values can significantly reduce the prediction error. Hyperparameter tuning is essential for optimizing the models' performance.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2022)

Add to Collection

Article Energy & Fuels

Forecasting and uncertainty analysis of day-ahead photovoltaic power using a novel forecasting method

Bo Gu et al.

Summary: This paper proposes a method to improve the accuracy of photovoltaic power forecasting by using a combination of algorithms such as FCM, WOA, LSSVM, and NPKDE. By optimizing model parameters and improving calculation speed and accuracy, the forecasting accuracy was significantly improved compared to other models. The NPKDE method accurately describes the probability density distribution of forecasting error.

APPLIED ENERGY (2021)

Add to Collection

Article Energy & Fuels

Peak oil and the low-carbon energy transition: A net-energy perspective

Louis Delannoy et al.

Summary: This paper explores the impact of using lower quality energy sources on the net-energy supply of oil products, finding that by 2050, half of the gross energy output will be needed for oil production. This challenges the feasibility of a rapid global transition to low-carbon energy, suggesting a renewed focus on net-energy issues in the peak oil debate.

APPLIED ENERGY (2021)

Add to Collection

Article Energy & Fuels

SolarNet: A hybrid reliable model based on convolutional neural network and variational mode decomposition for hourly photovoltaic power forecasting

Deniz Korkmaz

Summary: A novel convolutional neural network model SolarNet is proposed for short-term PV output power forecasting under different weather conditions and seasons. Experimental results show that the proposed method has higher accuracy and stability in short-term PV power forecasting, outperforming other deep learning methods.

APPLIED ENERGY (2021)

Add to Collection

Article Construction & Building Technology

Temporal characterization of minute-level PM2.5 variation within a local monitoring network using DWT-DTW

Yuli Fan et al.

Summary: The study integrates discrete wavelet transforms and dynamic time warping to formulate practical pollution process indicators. Empirical analysis in a campus network identified distinct information conveyed on different temporal scales, while a case study discovered four phases within a 3-day period, aiding in the discovery of potential pollution incidents.

BUILDING AND ENVIRONMENT (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 Green & Sustainable Science & Technology

PV power prediction in a peak zone using recurrent neural networks in the absence of future meteorological information

Donghun Lee et al.

Summary: The majority of daily PV power outputs are obtained around noon, making hourly PV power output prediction in a peak zone crucial for advanced operations. This study proposes two PV power output prediction models using LSTM and GRU, which outperform conventional models in predicting PV power in the peak zone by capturing hidden sequential patterns without using future meteorological information.

RENEWABLE ENERGY (2021)

Add to Collection

Article Computer Science, Information Systems

A rank-based framework through manifold learning for improved clustering tasks

Bionda Rozin et al.

Summary: This paper discusses the importance of diversified data preprocessing approaches for improving clustering tasks, with a focus on the successful application of rank-based manifold learning methods in unsupervised similarity learning, as well as the evaluation of the proposed clustering framework in experiments.

INFORMATION SCIENCES (2021)

Add to Collection

Article Green & Sustainable Science & Technology

Modelling global solar irradiance for any location on earth through regression analysis using high-resolution data

Dinesh Rajan Arumugham et al.

Summary: This study focuses on developing a highly accurate formulation to estimate solar parameters and predict solar irradiance for various cities around the world. Models generated through regression analysis perform better than existing models, making them efficient and reliable for universal global application.

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

A multi-step ahead photovoltaic power prediction model based on similar day, enhanced colliding bodies optimization, variational mode decomposition, and deep extreme learning machine

Qing Li et al.

Summary: The study proposed a similar day-based ultrashort-term multi-step ahead prediction model of photovoltaic power, which combines various optimization methods and algorithms. Experimental results demonstrated that the model has high accuracy in multi-step prediction, strong intelligence capabilities, and can be easily applied and popularized in practical projects.

ENERGY (2021)

Add to Collection

Article Engineering, Electrical & Electronic

A novel protection method for a wind farm collector line based on FCM clustering analysis

Kun Yu et al.

Summary: The proposed protection method based on fuzzy c-means clustering analysis accurately trips the faulty collector line by considering DFIG feeding current under different fault conditions. This protection method improves relay adaptability under variable wind farm operation conditions.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

DTW-NN: A novel neural network for time series recognition using dynamic alignment between inputs and weights

Brian Kenji Iwana et al.

KNOWLEDGE-BASED SYSTEMS (2020)

Add to Collection

Article Green & Sustainable Science & Technology

Prediction short-term photovoltaic power using improved chicken swarm optimizer - Extreme learning machine model

Zhi-Feng Liu et al.

JOURNAL OF CLEANER PRODUCTION (2020)

Add to Collection

Article Physics, Multidisciplinary

A pattern representation of stock time series based on DTW

Tian Han et al.

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (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 Acoustics

Correlation distance skip connection denoising autoencoder (CDSK-DAE) for speech feature enhancement

Alzahra Badi et al.

APPLIED ACOUSTICS (2020)

Add to Collection

Article Thermodynamics

Improved quantile convolutional neural network with two-stage training for daily-ahead probabilistic forecasting of photovoltaic power

Qian Huang et al.

ENERGY CONVERSION AND MANAGEMENT (2020)

Add to Collection

Article Engineering, Multidisciplinary

Deep learning and wavelet transform integrated approach for short-term solar PV power prediction

Manohar Mishra et al.

MEASUREMENT (2020)

Add to Collection

Article Energy & Fuels

Study on power consumption load forecast based on K-means clustering and FCM-BP model

Bian Haihong et al.

ENERGY REPORTS (2020)

Add to Collection

Article Energy & Fuels

Mid-to-long term wind and photovoltaic power generation prediction based on copula function and long short term memory network

Shuang Han et al.

APPLIED ENERGY (2019)

Add to Collection

Article Thermodynamics

Probability modeling for PV array output interval and its application in fault diagnosis

Haizheng Wang et al.

ENERGY (2019)

Add to Collection

Article Energy & Fuels

Iterative multi-task learning for time-series modeling of solar panel PV outputs

Tahasin Shireen et al.

APPLIED ENERGY (2018)

Add to Collection

Article Green & Sustainable Science & Technology

Regional forecasts and smoothing effect of photovoltaic power generation in Japan: An approach with principal component analysis

Joao Gari da Silva Fonseca Junior et al.

RENEWABLE ENERGY (2014)

Add to Collection

Article Green & Sustainable Science & Technology

A Weather-Based Hybrid Method for 1-Day Ahead Hourly Forecasting of PV Power Output

Hong-Tzer Yang et al.

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY (2014)

Add to Collection

Article Engineering, Multidisciplinary

Forecasting Power Output of Photovoltaic Systems Based on Weather Classification and Support Vector Machines

Jie Shi et al.

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS (2012)

Add to Collection

© Peeref 2019-2024. All rights reserved.