Reducing Wind Power Forecast Error Based on Machine Learning Algorithms and Producers Merging

Srpak, Dunja; Havaš, Ladislav; Skok, Srđan; Polajžer, Boštjan

doi:10.1109/eeeic.2019.8783423

Cited by 5 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 2 summarizes the approach that is based on the machine intelligence (MI) paradigm [9][10][11].…”

Section: Instrumentsmentioning

confidence: 99%

Revolutionizing Sustainable Energy Production with Quantum Artificial Intelligence: Applications in Autonomous Robotics and Data Management

Baklaga

2023

GLCE

View full text Add to dashboard Cite

The present commentary delineates the scope of quantum-based artificial intelligence (AI) in confronting the escalating need for eco-friendly sources of energy. Contemporary concerns regarding the detrimental impacts of conventional energy sources on the environment have led to the exploration of alternative and sustainable options. The amalgamation of quantum computing and AI is a potentially effective remedy for the existing energy crisis. The present analysis explores the theoretical underpinnings of quantum artificial intelligence and its palpable ramifications in the energy realm. It highlights the capacity of quantum AI to enhance energy efficiency, reduce waste, and minimize the detrimental impact of energy production on the environment. Experimental techniques, such as solar irradiation, wind velocity, and pumped-water energy storage, were utilized to demonstrate the effectiveness of quantum AI in predicting renewable energy generation. Several information models and machine learning techniques have been examined to identify models that yield accurate predictions of renewable energy generation. The results demonstrate that quantum AI can easily perform complex quantum sub-atomic simulations, making it a valuable tool in the fields of computational science and molecular physics. A quantum AI-powered automated robotic system is proposed to optimize energy management. The implementation of a monitoring system that monitors energy consumption levels, mechanizes the production and distribution processes of energy, and anticipates future energy demands in real time, renders it an indispensable device for both energy conglomerates and policymakers. This study ascertains that the amalgamation of quantum computing and artificial intelligence harbors substantial potential for sustainable energy generation, marked by streamlined energy production, minimal waste generation, and ecoconservation. The present investigation furnishes insightful observations pertaining to the potential benefits of quantum artificial intelligence for the purpose of ensuring sustainable energy production. Additionally, it presents a roadmap for future research in this area.

show abstract

“…Figure 2 summarizes the approach that is based on the machine intelligence (MI) paradigm [9][10][11].…”

Section: Instrumentsmentioning

confidence: 99%

Revolutionizing Sustainable Energy Production with Quantum Artificial Intelligence: Applications in Autonomous Robotics and Data Management

Baklaga

2023

GLCE

View full text Add to dashboard Cite

show abstract

“…For wind-energy predictions, statistical methods were used in the early stage [17,18]. Recent studies employed artificial intelligence and machine-learning techniques in wind-energy predictions, such as support-vector machines [16][17][18][19], random forest classification algorithms [20,21], gradient boosting decision trees [22], adaptive neuro-fuzzy inference system (ANFIS) [23], artificial neural network [24][25][26][27][28][29][30][31][32][33][34][35][36][37][38], and long short-term memory networks [39-45]. The machine-learning techniques were able to capture data trends in forecasting wind energy.…”

Section: The Status Of Machine-learning Technology Used In Renewable-...mentioning

confidence: 99%

“…Gaussian process regression(GPR), Support vector regression(SVR), Artificial neural networks(ANN) [16]; xGBoost regression, SVR, Random forest(RF) [18]; Least squares support vector machine(SVM) [19]; SVR, ANN, Gradient boosting(GB), RF [20]; RF [21]; GB trees [22]; Multi-layer perceptron(MLP) [24]; Deep neural network(DNN)-principal component analysis [25]; Feedforward ANN [26]; Efficient deep convolution neural network [27,34]; Linear regression, neural networks, SVR [28]; Convolutional neural networks(CNN) [29,37]; DNN [30,31] [114]; Extreme learning machine(ELM) [115,116]; Empirical mode decomposition(EMD)-stacked auto-encoders-ELM [117]; Pattern sequence-based forecasting [118]…”

Section: Wind Artificial Intelligencementioning

confidence: 99%

A Survey of Machine Learning Models in Renewable Energy Predictions

et al. 2020

View full text Add to dashboard Cite

The use of renewable energy to reduce the effects of climate change and global warming has become an increasing trend. In order to improve the prediction ability of renewable energy, various prediction techniques have been developed. The aims of this review are illustrated as follows. First, this survey attempts to provide a review and analysis of machine-learning models in renewable-energy predictions. Secondly, this study depicts procedures, including data pre-processing techniques, parameter selection algorithms, and prediction performance measurements, used in machine-learning models for renewable-energy predictions. Thirdly, the analysis of sources of renewable energy, values of the mean absolute percentage error, and values of the coefficient of determination were conducted. Finally, some possible potential opportunities for future work were provided at end of this survey.

show abstract

“…Adding to the two renewable energy sources, coal power and energy production are the speediest energy sources today. Alternative sources are any kind of energy that can be harvested in nature and is renewable or nonpolluting [1][2][3][4]. It may be found in a number of different forms, including sun's electricity, solar energy, electricity, geothermal heat, waves, tide, and hydroelectricity.…”

Section: Introductionmentioning

confidence: 99%

“…Many methodologies were highlighted and techniques were suggested by the use of three fundamental learning concepts [6]. In addition, several types of research are produced from renewable generation forecasting via the use of a single AI framework [4]. Unfortunately, it is challenging to enhance prediction power that used a simple device model owing to the varied datasets, time stages, predictions ranges, parameters and measurement and management [7][8][9][10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Prophetic Energy Assessment with Smart Implements in Hydroelectricity Entities Using Artificial Intelligence Algorithm

Alqahtani

Kshirsagar

Manoharan³

et al. 2022

International Transactions on Electrical Energy Systems

View full text Add to dashboard Cite

An encouraging development is the quick expansion of renewable energy extraction. Harnessing renewable energy is economically feasible at the current rate of technological advancement. Traditional energy sources, such as coal, petroleum, and hydrocarbons, which have negative effects on the environment, are coming under more social and financial pressure. Companies need more solar and wind power because this calls for a well-balanced mix of renewable resources and a higher proportion of alternative energy sources. Sustainable energy can be captured using a variety of techniques. Massive scale and small-sized are the two most prevalent techniques. No renewable energy source possesses an inherent property that restricts how it may be managed or how it can be planned to produce electricity. A number of factors have contributed to a growth in the use of alternative sources, one of which is to mitigate the effects of rising temperatures. To improve the ability to estimate renewable energy, various modeling approaches have been created. This region might use an HRES to give many sources with the inclusion of different energy sources. The inventiveness of solar and wind power and the brilliant ability of neural networks to handle complex time-series data signals have both aided in the prediction of sustainable energy. Therefore, this research will examine the numerous information models in order to determine which proposed models can provide accurate projections of renewable energy output, such as sunlight, wind, or pumped storage. In the fields of sustainable energy predictions, a number of machine learning methods, such as multilayer perceptions MLP, RNN CNN, and LSTM designs, are frequently utilized. This form of modeling uses historical data to predict potential values and can predict short-term patterns in solar and wind generation.

show abstract

Reducing Wind Power Forecast Error Based on Machine Learning Algorithms and Producers Merging

Cited by 5 publications

References 15 publications

Revolutionizing Sustainable Energy Production with Quantum Artificial Intelligence: Applications in Autonomous Robotics and Data Management

Revolutionizing Sustainable Energy Production with Quantum Artificial Intelligence: Applications in Autonomous Robotics and Data Management

A Survey of Machine Learning Models in Renewable Energy Predictions

Prophetic Energy Assessment with Smart Implements in Hydroelectricity Entities Using Artificial Intelligence Algorithm

Contact Info

Product

Resources

About