A comparative study of optimization methods for improving artificial neural network performance

Kajornrit, Jesada

doi:10.1109/iciteed.2015.7408908

Cited by 10 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The need to forecast the power generation of renewable energy sources is recognized internationally [21]. Various ML methods are applied for this problem: artificial neural networks [22]- [24], population-based algorithms [25], support vector regression [26], [27], regression trees, and ensembles of regression tree [27], [28]. However, at the time of this writing, the authors do not know an internationally recognized reliable industry solution to the problem of photovoltaic power plants generation forecasting, implemented into the process-related activities of the key power industry stakeholders world-wide.…”

Section: Errorneous Industry Cases For Power Generation Forecasting P...mentioning

confidence: 99%

Inappropriate machine learning application in real power industry cases

Khalyasmaa

Matrenin

Eroshenko

2022

IJECE

View full text Add to dashboard Cite

<span>Global digital transformation of the energy sector has led to the emergence of multiple digital platform solutions, the implementation of which have revealed new problems associated with continuous growth of data volumes requiring new approaches to their processing and analysis. This article is devoted to the improper application of machine learning approaches and flawed interpretation of their output at various stages of decision support systems development: data collection; model development, training and testing as well as industrial implementation. As a real industrial case study, the article examines the power generation forecasting problem of photovoltaic power plants. The authors supplement the revealed problems with the corresponding recommendation for industrial specialists and software developers.</span>

show abstract

Section: Errorneous Industry Cases For Power Generation Forecasting P...mentioning

confidence: 99%

Inappropriate machine learning application in real power industry cases

Khalyasmaa

Matrenin

Eroshenko

2022

IJECE

View full text Add to dashboard Cite

show abstract

“…Sometimes, BP network technique falls in local minimum due to gradient descent technique. Existence of local minimum condition does not guarantee an approximation so there are many situations in which it will oscillate forever [13,14]. This paper predicts PV power during haze and clear weather.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Power Forecasting Model for Photovoltaic Plants Based on Neural Network with Air Quality Index

Khan

Zhu

Yao

et al. 2017

International Journal of Photoenergy

View full text Add to dashboard Cite

High concentration of greenhouse gases in the atmosphere has increased dependency on photovoltaic (PV) power, but its random nature poses a challenge for system operators to precisely predict and forecast PV power. The conventional forecasting methods were accurate for clean weather. But when the PV plants worked under heavy haze, the radiation is negatively impacted and thus reducing PV power; therefore, to deal with haze weather, Air Quality Index (AQI) is introduced as a parameter to predict PV power. AQI, which is an indication of how polluted the air is, has been known to have a strong correlation with power generated by the PV panels. In this paper, a hybrid method based on the model of conventional back propagation (BP) neural network for clear weather and BP AQI model for haze weather is used to forecast PV power with conventional parameters like temperature, wind speed, humidity, solar radiation, and an extra parameter of AQI as input. The results show that the proposed method has less error under haze condition as compared to conventional model of neural network.

show abstract