Maximum wind speed forecasting using historical data and artificial neural networks modeling

Şen, Mehmet Umut; Özcan, Muciz

doi:10.31593/ijeat.800937

Cited by 4 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is one of nature's cleanest and most inexhaustible energy sources [5]. The amount of energy emitted by the sun is approximately 28000 times that consumed by humans worldwide in one year [6][7][8]. According to research conducted by the International Energy Agency (IEA), sunlight hitting the earth for 90 minutes can provide enough energy to power the world for one year.…”

Section: Introductionmentioning

confidence: 99%

Technoeconomic Analysis of 1 MWp Grid Connected Solar Power Plant in Konya (Türkiye)

2023

Teh. vjesn.

View full text Add to dashboard Cite

Global warming is seen as one of the most important problems that trigger climate change in the world. The leading cause of global warming is the high amount of greenhouse gases released into the atmosphere. Countries are creating policies to encourage the use of renewable energy sources to control greenhouse gas emissions. Many universities in Türkiye have enough campus areas to generate electricity from renewable energy sources. The main purpose of this article is to analyze the feasibility of developing a solar power plant at Necmettin Erbakan University. This article proposes a 1MW solar power plant in Necmettin Erbakan University Köyceğiz Campus located in the city of Konya, which has the largest surface area in Türkiye. The technical feasibility of the proposed PV plant was analyzed using PVGIS, PVWatts, and PVsyst software. For this purpose, the economic and environmental aspects of the power plant to be established on campus were investigated through the production data. 1 MWp solar power plant can generate approximately 1685.78 MWh of electricity per year while reducing 820.21 tCO2 greenhouse gas emissions. The technical data obtained in the analyses made with PVGIS, PVWatts, and PVsyst software are similar.

show abstract

Section: Introductionmentioning

confidence: 99%

Technoeconomic Analysis of 1 MWp Grid Connected Solar Power Plant in Konya (Türkiye)

2023

Teh. vjesn.

View full text Add to dashboard Cite

show abstract

“…Determining the topology that does not match the needs caused overfitting or underfitting in neural networks. Several researchers have conducted research to determine the neural network topology in various ways: methods based solely on the number of input and output attributes ( Sartori & Antsaklis, 1991 ; Tamura & Tateishi, 1997 ), trial and error ( Blanchard & Samanta, 2020 ; Madhiarasan, 2020 ; Madhiarasan & Deepa, 2016 ; Madhiarasan & Deepa, 2017 ; Şen & Özcan, 2021 ) , and the rule of thumb ( Bakhashwain & Sagheer, 2021 ; Carballal et al, 2021 ; Rahman et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

Determining the number of hidden layer and hidden neuron of neural network for wind speed prediction

Rachmatullah

Santoso

Surendro

2021

PeerJ Computer Science

View full text Add to dashboard Cite

Artificial neural network (ANN) is one of the techniques in artificial intelligence, which has been widely applied in many fields for prediction purposes, including wind speed prediction. The aims of this research is to determine the topology of neural network that are used to predict wind speed. Topology determination means finding the hidden layers number and the hidden neurons number for corresponding hidden layer in the neural network. The difference between this research and previous research is that the objective function of this research is regression, while the objective function of previous research is classification. Determination of the topology of the neural network using principal component analysis (PCA) and K-means clustering. PCA is used to determine the hidden layers number, while clustering is used to determine the hidden neurons number for corresponding hidden layer. The selected topology is then used to predict wind speed. Then the performance of topology determination using PCA and clustering is then compared with several other methods. The results of the experiment show that the performance of the neural network topology determined using PCA and clustering has better performance than the other methods being compared. Performance is determined based on the RMSE value, the smaller the RMSE value, the better the neural network performance. In future research, it is necessary to apply a correlation or relationship between input attribute and output attribute and then analyzed, prior to conducting PCA and clustering analysis.

show abstract

Developing an Optimization Model for Minimizing Solid Waste Collection Costs

CENGİZ,

ŞEN,

ÖZCAN

2023

Sakarya University Journal of Science

View full text Add to dashboard Cite

With the increase in population in cities, the number of solid waste to be collected has also increased. Because the garbage collection route must be traveled repeatedly, even minor improvements in these routes can result in a significant increase in fuel usage. Shortening the journey would provide a significant contribution to lowering fuel expenses in all towns, especially given the rising cost of fossil fuels. Furthermore, lowering fuel usage is critical for Turkey to meet its national objectives under the Paris Agreement. The Simulated Annealing (SA) algorithm, one of the heuristic optimization techniques used to identify the best solutions to complicated problems, is employed to solve the routing problem of solid waste collection vehicles in this study. This method, which was inspired by the metal annealing process, stands out for its ability to avoid regional minima while looking for the optimal solution. The applicant region was selected as the Kosova Neighborhood of Konya's Selçuklu District. The container distances needed for the method to execute were acquired by extracting the coordinates of the containers. Kosova Neighborhood was separated into 7 distinct regions due to the restricted capacity of rubbish collection vans. All regions were analyzed independently, and the best feasible routes were estimated using the SA algorithm approach, and the results were compared to the greedy algorithm findings. The SA algorithm outperformed the greedy algorithm by 26.49%.

show abstract

Maximum wind speed forecasting using historical data and artificial neural networks modeling

Cited by 4 publications

References 14 publications

Technoeconomic Analysis of 1 MWp Grid Connected Solar Power Plant in Konya (Türkiye)

Technoeconomic Analysis of 1 MWp Grid Connected Solar Power Plant in Konya (Türkiye)

Determining the number of hidden layer and hidden neuron of neural network for wind speed prediction

Developing an Optimization Model for Minimizing Solid Waste Collection Costs

Contact Info

Product

Resources

About