Wind Speed Prediction Using Artificial Neural Networks Based on Multiple Local Measurements in Eskisehir

Filik, Ümmühan Başaran; Filik, Tansu

doi:10.1016/j.egypro.2016.12.147

Cited by 83 publications

(19 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Basaran Filik and Tansu Filik in [8] analyzed three different models of predicting wind speed using ANNs. The first model used historical wind speed as the input; the second used historical wind speed and temperature as input while the third had historical wind speed, temperature, and pressure as inputs.…”

Section: Related Workmentioning

confidence: 99%

A Short-Term Wind Power Forecasting Approach using ANFIS

Mathenge¹,

Murage²,

Nderu³

2021

IRJIET

View full text Add to dashboard Cite

In recent times, there has been a growing penetration of wind power in electrical grids globally. On one hand, this has led to the reduction in the cost of unit power while on the other hand brought about the challenge of ensuring grid reliability in cases where the penetration of wind power is high. This is brought about by the high intermittency and limited predictability of wind power hence making it a non-dispatchable resource, unlike conventional power sources. As a result of this, there has been a parallel growth in the research around wind speed and wind power forecasting techniques to ensure that the maximum benefits of wind power are realized at the cheapest cost possible. Neural networks have been at the core of this research owing to their ability to learn, versatility in handling time-series data, and their strength in establishing non-linear relationships between input and output datasets. In this paper, a hybrid Adaptive Neuro-Fuzzy Inference System (ANFIS) is enhanced using previous hour wind power and wind speed data to improve its accuracy in short-term wind forecasting.

show abstract

Section: Related Workmentioning

confidence: 99%

A Short-Term Wind Power Forecasting Approach using ANFIS

Mathenge¹,

Murage²,

Nderu³

2021

IRJIET

View full text Add to dashboard Cite

show abstract

“…Another common method relies on the use of Artificial Neural Networks (ANNs), for both irradiance [65] and wind speed [66]. An ANN is composed of a number of highly interconnected processing elements Y i,j , called neurons, where each output follows Equation (2):…”

Section: Data Sourcesmentioning

confidence: 99%

Operational Simulation Environment for SCADA Integration of Renewable Resources

et al. 2020

View full text Add to dashboard Cite

The complexity of power systems is rising mainly due to the expansion of renewable energy generation. Due to the enormous variability and uncertainty associated with these types of resources, they require sophisticated planning tools so that they can be used appropriately. In this sense, several tools for the simulation of renewable energy assets have been proposed. However, they are traditionally focused on the simulation of the generation process, leaving the operation of these systems in the background. Conversely, more expert SCADA operators for the management of renewable power plants are required, but their training is not an easy task. SCADA operation is usually complex, due to the wide set of information available. In this sense, simulation or co-simulation tools can clearly help to reduce the learning curve and improve their skills. Therefore, this paper proposes a useful simulator based on a JavaScript engine that can be easily connected to any renewable SCADAs, making it possible to perform different simulated scenarios for novel operator training, as if it were a real facility. Using this tool, the administrators can easily program those scenarios allowing them to sort out the lack of support found in setting up facilities and training of novel operator tasks. Additionally, different renewable energy generation models that can be implemented in the proposed simulator are described. Later, as a use example of this tool, a study case is also performed. It proposes three different wind farm generation facility models, based on different turbine models: one with the essential generation turbine function obtained from the manufacturer curve, another with an empirical model using monotonic splines, and the last one adding the most important operational states, making it possible to demonstrate the usefulness of the proposed simulation tool.

show abstract

“…Senthil Kumar [67] presented three different ANN-based models for wind speed prediction, such as a back-propagation network (BPN), non-linear auto-regressive with exogenous inputs (NARX), and radial basis function (RBF). The LSTM optimization algorithm was also used the recurrent neural networks (RNNs) to predict the wind speed for daily and monthly basis [68] and finally, a univariate single layer RNN was recommended for wind speed forecasting. Jaume et al [66] proposed deep learning approaches for wind speed prediction and different structures including MLP, CNN and RNN were applied in large wind dataset.…”

Section: Introductionmentioning

confidence: 99%

Prospective Methodologies in Hybrid Renewable Energy Systems for Energy Prediction Using Artificial Neural Networks

et al. 2021

View full text Add to dashboard Cite

This paper presents a comprehensive review of machine learning (ML) based approaches, especially artificial neural networks (ANNs) in time series data prediction problems. According to literature, around 80% of the world’s total energy demand is supplied either through fuel-based sources such as oil, gas, and coal or through nuclear-based sources. Literature also shows that a shortage of fossil fuels is inevitable and the world will face this problem sooner or later. Moreover, the remote and rural areas that suffer from not being able to reach traditional grid power electricity need alternative sources of energy. A “hybrid-renewable-energy system” (HRES) involving different renewable resources can be used to supply sustainable power in these areas. The uncertain nature of renewable energy resources and the intelligent ability of the neural network approach to process complex time series inputs have inspired the use of ANN methods in renewable energy forecasting. Thus, this study aims to study the different data driven models of ANN approaches that can provide accurate predictions of renewable energy, like solar, wind, or hydro-power generation. Various refinement architectures of neural networks, such as “multi-layer perception” (MLP), “recurrent-neural network” (RNN), and “convolutional-neural network” (CNN), as well as “long-short-term memory” (LSTM) models, have been offered in the applications of renewable energy forecasting. These models are able to perform short-term time-series prediction in renewable energy sources and to use prior information that influences its value in future prediction.

show abstract

Wind Speed Prediction Using Artificial Neural Networks Based on Multiple Local Measurements in Eskisehir

Cited by 83 publications

References 10 publications

A Short-Term Wind Power Forecasting Approach using ANFIS

A Short-Term Wind Power Forecasting Approach using ANFIS

Operational Simulation Environment for SCADA Integration of Renewable Resources

Prospective Methodologies in Hybrid Renewable Energy Systems for Energy Prediction Using Artificial Neural Networks

Contact Info

Product

Resources

About