☆ 4.6 Article

Direct Short-Term Net Load Forecasting Based on Machine Learning Principles for Solar-Integrated Microgrids

IEEE ACCESS (2023)

Related references

Note: Only part of the references are listed.

Article Thermodynamics

Short-term electric net load forecasting for solar-integrated distribution systems based on Bayesian neural networks and statistical post-processing

Georgios Tziolis et al.

Summary: A new methodology based on a Bayesian neural network model was proposed for direct short-term net load forecasting at the distribution level. The optimized model achieved high forecasting accuracies, and the statistical post-processing further improved the accuracy. The results demonstrated the suitability of the methodology for distribution feeders with diverse PV penetration shares.

ENERGY (2023)

Add to Collection

Article Energy & Fuels

A historical weather forecast dataset from the European Centre for Medium-Range Weather Forecasts (ECMWF) for energy forecasting

Dazhi Yang et al.

Summary: Weather is a crucial factor for power generation and energy consumption, and energy forecasting models often rely on numerical weather prediction. This article offers an NWP forecast dataset from ECMWF for the energy forecasting community, along with case studies on post-processing of solar forecasts.

SOLAR ENERGY (2022)

Add to Collection

Article Engineering, Electrical & Electronic

FPSeq2Q: Fully Parameterized Sequence to Quantile Regression for Net-Load Forecasting With Uncertainty Estimates

Anthony Faustine et al.

Summary: This paper presents a parameterized deep quantile regression method for short-term probabilistic net-load forecasting at the distribution level. A Deep Neural Network (DNN) is used to learn both the quantile fractions and quantile values of the quantile function, and a scoring metric is proposed to reflect the trade-off between predictive uncertainty performance and forecast accuracy.

IEEE TRANSACTIONS ON SMART GRID (2022)

Add to Collection

Article Energy & Fuels

An Edge Computing-oriented Net Power Forecasting for PV-assisted Charging Station: Model Complexity and Forecasting Accuracy Trade-off

Jiaqi Shi et al.

Summary: This article presents a simplified approach for net power prediction in PV-assisted charging stations (PVCS) and demonstrates its excellent performance on an edge computing platform.

APPLIED ENERGY (2022)

Add to Collection

Article Green & Sustainable Science & Technology

A hybrid methodology for distribution level photovoltaic power production forecasting verified at the distribution system of Cyprus

Spyros Theocharides et al.

Summary: Accurate PV power forecasting is essential for integrating solar electricity efficiently. This study proposes a novel method for providing day-ahead aggregated PV production forecasts for distributed PV systems. By using clustering and up-scaling, the aggregated PV generation was successfully estimated.

IET RENEWABLE POWER GENERATION (2022)

Add to Collection

Article Construction & Building Technology

Probabilistic electrical load forecasting for buildings using Bayesian deep neural networks

Lei Xu et al.

Summary: This study presents three Bayesian deep neural network models for probabilistic building electrical load forecasting. The models utilize deep neural networks and the dropout technique to quantify model uncertainties. Experimental results show that all three models perform satisfactorily, with the Bayesian LSTM model achieving the best performance and satisfactory load forecasting accuracy with only 10-hour lagged electrical loads.

JOURNAL OF BUILDING ENGINEERING (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

GA-Reinforced Deep Neural Network for Net Electric Load Forecasting in Microgrids with Renewable Energy Resources for Scheduling Battery Energy Storage Systems

Chaoran Zheng et al.

Summary: This paper predicts the net electric load of a microgrid using a deep neural network and introduces a genetic algorithm to improve the prediction accuracy. The results show a significant reduction in errors compared to the BP neural network prediction.

ALGORITHMS (2022)

Add to Collection

Article Energy & Fuels

Data processing and quality verification for improved photovoltaic performance and reliability analytics

Andreas Livera et al.

Summary: Data integrity is essential for the analysis of photovoltaic systems, with data quality routines developed to ensure fidelity and accuracy. Techniques such as listwise deletion are effective for up to 10% invalid data, while data inference techniques are more accurate for missing data rates above 10%. Time series reconstruction using the Sandia PV Array Performance Model yielded the lowest error for PV performance analysis, even at high missing data rates.

PROGRESS IN PHOTOVOLTAICS (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 Energy & Fuels

Comparative Analysis of Machine Learning Models for Day-Ahead Photovoltaic Power Production Forecasting

Spyros Theocharides et al.

Summary: The study evaluates the day-ahead PV production forecasting performance of different machine learning models under different supervised learning regimes, finding that the performance is strongly dependent on various factors such as the timeframe of the train set and application of irradiance condition filters. Results show that utilizing calculated input parameters for training can lead to accurate forecasting and that the optimally constructed Bayesian neural network outperformed all other machine learning models in achieving forecasting accuracies lower than 5%.

ENERGIES (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Multi-energy net load forecasting for integrated local energy systems with heterogeneous prosumers

Bin Zhou et al.

Summary: This paper proposes a multi-energy forecasting framework based on deep learning methodology to predict the electrical, thermal and gas net load of integrated local energy systems. By qualitatively analyzing, clustering, and predicting heterogeneous prosumers, accurate forecasts for multiple energy producers are achieved.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2021)

Add to Collection

Article Energy & Fuels

Short-Term Net Load Forecasting with Singular Spectrum Analysis and LSTM Neural Networks

Akylas Stratigakos et al.

Summary: This study proposes a hybrid approach combining Singular Spectrum Analysis (SSA)-based decomposition and Artificial Neural Networks (ANNs) for day-ahead hourly load forecasting. Results show that the combination of LSTM and SAA provides the best overall performance in the presence of exogenous features.

ENERGIES (2021)

Add to Collection

Article Energy & Fuels

Short-Term Load Forecasting Using Neural Networks with Pattern Similarity-Based Error Weights

Grzegorz Dudek

Summary: Weighting individual errors of training samples in the loss function makes the learning process more sensitive to the neighborhood of the test pattern, thereby improving forecasting accuracy.

ENERGIES (2021)

Add to Collection

Article Thermodynamics

Prediction of solar energy guided by pearson correlation using machine learning

Imane Jebli et al.

Summary: This paper presents a solar energy forecasting approach based on machine and deep learning techniques, evaluating its relevance and performance in real-time and short-term solar energy predictions. The study found that RF and ANN provided higher accuracy compared to LR and SVR, with ANN performing well in both real-time and short-term predictions.

ENERGY (2021)

Add to Collection

Proceedings Paper Energy & Fuels

Direct Net Load Forecasting Using Adaptive Neuro Fuzzy Inference System

Gamal Aburiyana et al.

Summary: Electricity generated from renewable resources such as wind and solar energy is considered sustainable and emissions free, making them essential in meeting global load demand. However, the stochastic nature of wind and solar power adds variability and uncertainty to power systems, making it challenging for system operators to maintain balance. Accurate net load forecasts are crucial for ensuring reliable and cost-effective hybrid power system operation.

2021 IEEE ELECTRICAL POWER AND ENERGY CONFERENCE (EPEC) (2021)

Add to Collection

Article Computer Science, Information Systems

Machine Learning Based PV Power Generation Forecasting in Alice Springs

Khizir Mahmud et al.

Summary: This study provides a machine learning-based PV power generation forecasting for both short and long terms. Random Forest Regression is found to perform better for the dataset, and the impact of data normalization on forecasting performance is analyzed. The study may assist grid operators in choosing an appropriate PV power forecasting algorithm and planning for generation volatility.

IEEE ACCESS (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Using Bayesian Deep Learning to Capture Uncertainty for Residential Net Load Forecasting

Mingyang Sun et al.

IEEE TRANSACTIONS ON POWER SYSTEMS (2020)

Add to Collection

Article Physics, Multidisciplinary

Selecting optimal lag order in Ljung-Box test

Hossein Hassani et al.

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (2020)

Add to Collection

Article Engineering, Electrical & Electronic

High-resolution net load forecasting for micro-neighbourhoods with high penetration of renewable energy sources

P. Kobylinski et al.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2020)

Add to Collection

Article Energy & Fuels

Day-ahead photovoltaic power production forecasting methodology based on machine learning and statistical post-processing

Spyros Theocharides et al.

APPLIED ENERGY (2020)

Add to Collection

Article Energy & Fuels

Grey System Theory Based Net Load Forecasting for High Renewable Penetrated Power Systems

Sreenu Sreekumar et al.

TECHNOLOGY AND ECONOMICS OF SMART GRIDS AND SUSTAINABLE ENERGY (2020)

Add to Collection

Article Computer Science, Information Systems

Short-Term Photovoltaic Power Forecasting Using an LSTM Neural Network and Synthetic Weather Forecast

Mohammad Safayet Hossain et al.

IEEE ACCESS (2020)

Add to Collection

Article Computer Science, Information Systems

Photovoltaic Power Forecasting With a Hybrid Deep Learning Approach

Gangqiang Li et al.

IEEE ACCESS (2020)

Add to Collection

Article Computer Science, Information Systems

A Deep Learning Method for Short-Term Residential Load Forecasting in Smart Grid

Ye Hong et al.

IEEE ACCESS (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network

Weicong Kong et al.

IEEE TRANSACTIONS ON SMART GRID (2019)

Add to Collection

Article Chemistry, Multidisciplinary

An Ultrashort-Term Net Load Forecasting Model Based on Phase Space Reconstruction and Deep Neural Network

Fei Mei et al.

APPLIED SCIENCES-BASEL (2019)

Add to Collection

Article Thermodynamics

Energy management in microgrid with considering high penetration of renewable resources and surplus power generation problem

Vahid Sohrabi Tabar et al.

ENERGY (2019)

Add to Collection

Article Computer Science, Information Systems

A New Hybrid Model for Short-Term Electricity Load Forecasting

Md Rashedul Haq et al.

IEEE ACCESS (2019)

Add to Collection

Article Computer Science, Information Systems

Short-Term Photovoltaic Power Forecasting Based on Long Short Term Memory Neural Network and Attention Mechanism

Hangxia Zhou et al.

IEEE ACCESS (2019)

Add to Collection

Article Computer Science, Information Systems

Multi-Scale Convolutional Neural Network With Time-Cognition for Multi-Step Short-Term Load Forecasting

Zhuofu Deng et al.

IEEE ACCESS (2019)

Add to Collection

Article Energy & Fuels

Blending distributed photovoltaic and demand load forecasts

Sue Ellen Haupt et al.

SOLAR ENERGY (2017)

Add to Collection

Article Energy & Fuels

Net load forecasts for solar-integrated operational grid feeders

Yinghao Chu et al.

SOLAR ENERGY (2017)

Add to Collection

Article Green & Sustainable Science & Technology

A Probabilistic Competitive Ensemble Method for Short-Term Photovoltaic Power Forecasting

Antonio Bracale et al.

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY (2017)

Add to Collection

Article Meteorology & Atmospheric Sciences

THE WEATHER RESEARCH AND FORECASTING MODEL Overview, System Efforts, and Future Directions

Jordan G. Powers et al.

BULLETIN OF THE AMERICAN METEOROLOGICAL SOCIETY (2017)

Add to Collection

Article Energy & Fuels

Short-term forecasting of power production in a large-scale photovoltaic plant

A. Mellit et al.

SOLAR ENERGY (2014)

Add to Collection

Article Green & Sustainable Science & Technology

Prediction of daily global solar irradiation data using Bayesian neural network: A comparative study

R. Yacef et al.

RENEWABLE ENERGY (2012)

Add to Collection

Article Economics

Large neural networks for electricity load forecasting: Are they overfitted?

HS Hippert et al.

INTERNATIONAL JOURNAL OF FORECASTING (2005)

Add to Collection

© Peeref 2019-2024. All rights reserved.