4.8 Article

Probabilistic modeling of future electricity systems with high renewable energy penetration using machine learning

Related references

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

Do multi-sector energy system optimization models need hourly temporal resolution? A case study with an investment and dispatch model applied to France

Behrang Shirizadeh et al.

Summary: The study compares the effects of two time-series aggregation methods on energy system optimization models, finding that reducing temporal resolution is relatively stable and has a small impact on the main output variables.

APPLIED ENERGY (2022)

Article Energy & Fuels

A deep generative model for probabilistic energy forecasting in power systems: normalizing flows

Jonathan Dumas et al.

Summary: The paper introduces a novel deep learning technique, normalizing flows, to produce accurate scenario-based probabilistic forecasts for power systems applications, addressing the challenges of renewable energy integration.

APPLIED ENERGY (2022)

Article Chemistry, Physical

Hybrid boosting algorithms and artificial neural network for wind speed prediction

Ayse Tugba Dosdogru et al.

Summary: Energy sources are crucial for national economic growth, with wind energy playing a significant role in low-carbon energy technologies. This study focuses on improving wind speed prediction by utilizing a hybrid approach of XGBoost, AdaBoost, and ANN, aiming to provide more accurate results for wind speed forecasting.

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY (2022)

Article Energy & Fuels

From investment optimization to fair benefit distribution in renewable energy community modelling

Valeria Casalicchio et al.

Summary: This paper develops an integrated method for the implementation of a linear bottom-up optimization model to address different aspects of energy communities. A case study is conducted to verify the effectiveness of the method, and the results show that Demand Side Management and the composition of the energy community have significant impacts on overall investment and energy consumption. The introduced fair distribution method ensures a proper economic return for each participant.

APPLIED ENERGY (2022)

Article Engineering, Electrical & Electronic

Forecasting of locational marginal price components with artificial intelligence and sensitivity analysis: A study under tropical weather and renewable power for the Mexican Southeast

A. Livas-Garcia et al.

Summary: This study presents a hybrid approach based on artificial intelligence and global sensitivity analysis to forecast electricity prices and determine the influence of external factors. The results show that different input variables have varying impacts on the components of electricity prices, such as seasonal factors and fuel prices.

ELECTRIC POWER SYSTEMS RESEARCH (2022)

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)

Article Green & Sustainable Science & Technology

Climatology of dark doldrums in Japan

Masamichi Ohba et al.

Summary: This study investigates the synoptic-scale summer weather patterns associated with dark doldrums in East Japan. It finds that frequent occurrences of dark doldrums are linked to four typical weather patterns, which are influenced by the monsoon rain front and the Okhotsk high-pressure system. The frequency of dark doldrum events also shows considerable interannual variability connected to climate variations in the tropical Indo-western Pacific.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2022)

Article Energy & Fuels

Phasing out coal: An impact analysis comparing five large-scale electricity market models

Arne Poestges et al.

Summary: The achievement of climate targets has a significant impact on energy sector modeling and decision-making processes. Various policy instruments have been developed to mitigate greenhouse gas emissions, including administrative and market-based mechanisms for phasing out coal-fired generation technologies. This study compares five large-scale electricity market models and analyzes their differences in evaluating the effects of two coal phase-out strategies. The results provide insights for both modelers and decision-makers, highlighting the influence of reference scenarios and the importance of technical aspects in evaluating policy instruments.

APPLIED ENERGY (2022)

Article Economics

Calibration of deterministic NWP forecasts and its impact on verification

Martin János Mayer et al.

INTERNATIONAL JOURNAL OF FORECASTING (2022)

Article Thermodynamics

An improved feedforward-long short-term memory modeling method for the whole-life-cycle state of charge prediction of lithium-ion batteries considering current-voltage-temperature variation

Shunli Wang et al.

Summary: In this paper, an improved feedforward-long short-term memory (FF-LSTM) modeling method is proposed for accurate whole-life-cycle state of charge (SOC) prediction of lithium-ion batteries. The method effectively considers the variations in current, voltage, and temperature. Experimental tests show that the battery capacity reduces significantly over time.

ENERGY (2022)

Article Green & Sustainable Science & Technology

Benefits of physical and machine learning hybridization for photovoltaic power forecasting

Martin Janos Mayer

Summary: This paper proposes a hybrid method combining physical and machine learning approaches for irradiance-to-power conversion in photovoltaic power forecasting. The study compares the performance of physical, data-driven, and hybrid methods for power forecasting of PV plants in Hungary. Results show that the hybrid method with physically calculated predictors significantly reduces errors compared to optimized physical models and machine learning without physical considerations. The separation and transposition modeling steps are found to be the most important in physical modeling. Optimization of physical model chains is important even in hybrid modeling. The guidelines and recommendations provided in this paper can help improve the accuracy of PV power forecasts.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2022)

Article Construction & Building Technology

Modeling and optimal energy operation considering probabilistic and sustainable renewable energy models and demand side management

Ling Li et al.

Summary: With the rapid economic development, sustainable development has gained attention as an economic and social strategy. The proposed EH model optimizes renewable resources and demand response programs to transform regional economic modes and promote sustainable development.

ENERGY AND BUILDINGS (2021)

Article Energy & Fuels

Mesoscale modeling of a Dunkelflaute event

Bowen Li et al.

Summary: This study investigated a Dunkelflaute event near the coast of Belgium and simulated it using the WRF model. Validation with measured data and sensitivity experiments revealed the potential and reliability of the WRF model in reproducing and forecasting boundary layer evolution during such events.

WIND ENERGY (2021)

Article Energy & Fuels

Extensive comparison of physical models for photovoltaic power forecasting

Martin Janos Mayer et al.

Summary: Physical modeling plays a crucial role in forecasting the power production of grid-connected PV power plants. Different model chains can lead to significant differences in forecast accuracy, with irradiance separation and transposition modeling identified as the most critical calculation steps. Wind speed forecasts have only a marginal effect on PV power prediction accuracy.

APPLIED ENERGY (2021)

Article Energy & Fuels

Assessing the performance of deep learning models for multivariate probabilistic energy forecasting

Aleksei Mashlakov et al.

Summary: This study aims to explore the application of global deep learning models for multivariate energy forecasting in power systems, and evaluate their performance. The results suggest that global models perform better in short-term forecasts of heterogeneous datasets, but can be affected by hyperparameter sensitivity and hardware limitations as dataset dimensionality grows.

APPLIED ENERGY (2021)

Review Green & Sustainable Science & Technology

Critical review of renewable generation datasets and their implications for European power system models

Alexander Kies et al.

Summary: In the study of the transition to a highly renewable European power system, significant differences and cost disparities of about 10% were found among commonly used datasets. This underscores the importance of paying closer attention to the uncertainties in input data when utilizing large-scale energy system models.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2021)

Article Green & Sustainable Science & Technology

Probabilistic power output model of wind generating resources for network congestion management

SunOh Kim et al.

Summary: This study focuses on a probabilistic power output model of wind generating resources on Jeju Island in South Korea to address challenges in transmission grid planning and manage network congestion. By fitting Weibull distribution and conducting Monte Carlo simulations using historical data, a reliable probabilistic approach is proposed to reduce the risk of over-investment in power transmission facilities for high wind power penetration generation mix scenarios.

RENEWABLE ENERGY (2021)

Article Energy & Fuels

Comparison of power plant portfolios under the no energy mix target and national energy mix target using the mean-variance model

Andewi Rokhmawati

Summary: The study suggests that under Indonesia's energy policy, increasing the proportion of renewable energy in the national energy portfolio should be prioritized, with a focus on capacity to achieve economies of scale in investments.

ENERGY REPORTS (2021)

Article Energy & Fuels

Post-processing numerical weather prediction ensembles for probabilistic solar irradiance forecasting

Benedikt Schulz et al.

Summary: Probabilistic energy forecasting is crucial for integrating volatile power sources like solar energy into the electrical grid. Hybrid models combining physical and statistical methods have shown to be effective, with post-processing models proving to significantly improve the forecast performance of ensemble predictions and correct systematic biases.

SOLAR ENERGY (2021)

Article Environmental Sciences

Frequency and duration of low-wind-power events in Germany

Nils Ohlendorf et al.

ENVIRONMENTAL RESEARCH LETTERS (2020)

Article Meteorology & Atmospheric Sciences

The ERA5 global reanalysis

Hans Hersbach et al.

QUARTERLY JOURNAL OF THE ROYAL METEOROLOGICAL SOCIETY (2020)

Article Energy & Fuels

How to model European electricity load profiles using artificial neural networks

Christian Behm et al.

APPLIED ENERGY (2020)

Article Business

Environmental regulation and innovation in renewable energy technologies: Does the policy instrument matter?

Erik Hille et al.

TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE (2020)

Article Energy & Fuels

Deep learning framework to forecast electricity demand

Jatin Bedi et al.

APPLIED ENERGY (2019)

Article Green & Sustainable Science & Technology

Engerer2: Global re-parameterisation, update, and validation of an irradiance separation model at different temporal resolutions

Jamie M. Bright et al.

JOURNAL OF RENEWABLE AND SUSTAINABLE ENERGY (2019)

Article Green & Sustainable Science & Technology

Significant multidecadal variability in German wind energy generation

Jan Wohland et al.

WIND ENERGY SCIENCE (2019)

Article Multidisciplinary Sciences

Climatic characteristics of the 2010-2016 drought in the semiarid Northeast Brazil region

Jose A. Marengo et al.

ANAIS DA ACADEMIA BRASILEIRA DE CIENCIAS (2018)

Article Meteorology & Atmospheric Sciences

The Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2)

Ronald Gelaro et al.

JOURNAL OF CLIMATE (2017)

Article Engineering, Civil

Observational study of power-law approximation of wind profiles within an urban boundary layer for various wind conditions

Hideki Kikumoto et al.

JOURNAL OF WIND ENGINEERING AND INDUSTRIAL AERODYNAMICS (2017)

Proceedings Paper Construction & Building Technology

Modeling of solar energy potential in Souss-Massa area-Morocco, using intelligence Artificial Neural Networks (ANNs)

O. Nait Mensour et al.

MATERIALS & ENERGY I (2015) / MATERIALS & ENERGY II (2016) (2017)

Review Green & Sustainable Science & Technology

Machine learning methods for solar radiation forecasting: A review

Cyril Voyant et al.

RENEWABLE ENERGY (2017)

Article Meteorology & Atmospheric Sciences

Precipitation diagnostics of an exceptionally dry event in So Paulo, Brazil

Caio A. S. Coelho et al.

THEORETICAL AND APPLIED CLIMATOLOGY (2016)

Article Environmental Sciences

The role of capital costs in decarbonizing the electricity sector

Lion Hirth et al.

ENVIRONMENTAL RESEARCH LETTERS (2016)

Article Engineering, Electrical & Electronic

A probabilistic economic dispatch model and methodology considering renewable energy, demand and generator uncertainties

E. Arriagada et al.

ELECTRIC POWER SYSTEMS RESEARCH (2015)

Review Green & Sustainable Science & Technology

Development of hydro potential in Republic Srpska

Gordana Ostojic et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2013)

Article Energy & Fuels

Solar position algorithm for solar radiation applications

I Reda et al.

SOLAR ENERGY (2004)