Comparative Electrical Energy Yield Performance of Micro-Inverter PV Systems Using a Machine Learning Approach Based on a Mixed-Effect Model of Real Datasets

Le, Ngoc Thien; Benjapolakul, Watit

doi:10.1109/access.2019.2957381

Cited by 9 publications

(7 citation statements)

References 23 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…range of DR PV in this study is more accurate since its 95% CI. range is smaller, that is 1.7% (1.4% to 3.1%) as in Equation (23) compares to 2.3% (2% to 4.3%) in [21]. Finally, the Q-Q norm plot in Figure 7 confirms that the assumption of normal distribution of residual terms in linear decline model is rational.…”

Section: Linear Decline Model Based On Memsupporting

confidence: 55%

“…range is calculated as Equation (23)

\begin{matrix} true \\ right 95 % CI. & left = - \frac{false(- 3.4 \times 10^{- 3} false)}{2.98} (12) (100) \\ left to - \frac{false(- 7.6 \times 10^{- 3} false)}{2.98} (12) (100) \approx 1.4 % to 3.1 % \end{matrix}

Comparing to the 95% CI. range of

{DR}_{PV}

from 2% to 4.3% in our previous study [21] at yearly scale, the 95% CI. range of

{DR}_{PV}

in this study is more accurate since its 95% CI.…”

Section: Resultsmentioning

confidence: 79%

“…Comparing to the 95% CI. range of DR PV from 2% to 4.3% in our previous study [21] at yearly scale, the 95% CI. range of DR PV in this study is more accurate since its 95% CI.…”

Section: Linear Decline Model Based On Memmentioning

confidence: 67%

“…In addition, Paulo Fernando et al [10], utilized the power of mixed effects model combined with the first-order moving average model and first-order autoregressive errors model to predict the short-term electric power generation from Brazilian distributing utilities . Our previous study in [21] is the first study that found the average degradation rate of micro-inverter PV system of 3% per year by applying the linear version of mixed effects model. To the best of our knowledge, we are among the first research groups exploring the potential applications of mixed effects model to conduct data analytics in power engineering.…”

Section: Related Workmentioning

confidence: 99%

“…Figure 4 shows the data structure of the trend values

t_{i}

of the

i th

PV station during 6‐year period. In this scenario, PV stations are classified into only two groups: non‐shading (

S = 0

) and shading (

S = 1

) since we intend to compare the results to our previous study [21] at yearly scale. As the trend values tend to decrease over time, we propose two linear decline models as follows.…”

Section: The Mixed Effects Modelmentioning

confidence: 99%

See 4 more Smart Citations

Application of the mixed effects model for analysing photovoltaic datasets and interpreting into meaningful insights

Asdornwised

Chaitusaney

et al. 2021

IET Generation Trans & Dist

Self Cite

View full text Add to dashboard Cite

Energy power studies commonly apply the analysis of variance (ANOVA) method in data analysis context to find the significant difference among many compared groups or to evaluate the impact of an influential factor. However, most of the datasets in these studies are time series data or longitudinal data, which are collected from the same object over some periods. Therefore, violating the independent assumption of ANOVA is the error commonly made. This leads to the misinterpretation of the comparison tests. In this article, this problem is solved by providing the application of mixed effects model (MEM) as a viable alternative to the ANOVA. In detail, two models based on MEM are proposed to analyse the time series data of micro‐inverter PV stations located in Concord city, Massachusetts, USA. In the first scenario, the average models are implemented to compare the seasonal variation of monthly yield taking into account the effects of shading conditions and different orientations. In the second scenario, the linear regression model based on MEM is implemented to estimate and compare the decline rate in a 6‐year period of PV stations. The analysis results have shown that the models based on MEM performs better than ANOVA in interpreting raw time‐series dataset into meaningful insights.

show abstract

Section: Linear Decline Model Based On Memsupporting

confidence: 55%

“…range is calculated as Equation (23)

\begin{matrix} true \\ right 95 % CI. & left = - \frac{false(- 3.4 \times 10^{- 3} false)}{2.98} (12) (100) \\ left to - \frac{false(- 7.6 \times 10^{- 3} false)}{2.98} (12) (100) \approx 1.4 % to 3.1 % \end{matrix}

Comparing to the 95% CI. range of

{DR}_{PV}

from 2% to 4.3% in our previous study [21] at yearly scale, the 95% CI. range of

{DR}_{PV}

in this study is more accurate since its 95% CI.…”

Section: Resultsmentioning

confidence: 79%

“…Comparing to the 95% CI. range of DR PV from 2% to 4.3% in our previous study [21] at yearly scale, the 95% CI. range of DR PV in this study is more accurate since its 95% CI.…”

Section: Linear Decline Model Based On Memmentioning

confidence: 67%

Section: Related Workmentioning

confidence: 99%

“…Figure 4 shows the data structure of the trend values

t_{i}

of the

i th

PV station during 6‐year period. In this scenario, PV stations are classified into only two groups: non‐shading (

S = 0

) and shading (

S = 1

) since we intend to compare the results to our previous study [21] at yearly scale. As the trend values tend to decrease over time, we propose two linear decline models as follows.…”

Section: The Mixed Effects Modelmentioning

confidence: 99%

See 3 more Smart Citations

Application of the mixed effects model for analysing photovoltaic datasets and interpreting into meaningful insights

Asdornwised

Chaitusaney

et al. 2021

IET Generation Trans & Dist

Self Cite

View full text Add to dashboard Cite

show abstract

Annual Degradation Rate Analysis of Mono-Si Photovoltaics Systems in Thailand Using the Mixed Effects Method

Asdornwised

Chaitusaney

et al. 2021

IEEE Access

View full text Add to dashboard Cite

The annual degradation rate (DR) of photovoltaics (PV) system is a critical factor to evaluate the energy performance and the levelized cost of electricity (LCOE) during its operation lifetime. However, the DR of a particular system strongly depends on the technical configuration such as PV module and array, inverter configuration, and also the climatic conditions. Therefore, a real operation dataset of DR is necessary to PV engineer in order to estimate energy performance and the LCOE for a particular system. This article presents the annual DR for a group of PV systems in Bangkok, Thailand which share the same monocrystalline silicon solar cell and inverter brand, over a four-year period. Instead of using simple linear regression, we apply the linear mixed effects method to estimate the DR value, which is suitable to formula a time-series data. The annual DR was found about 2.7% per year, with the 95% confidence interval from 0.7% to 4.6% per year. Hence, the operation lifetime of PV system until it reaches 80% of their initial energy conversion performance is about 7 years, with the 95% confidence interval from 4 years to 28 years. The resulting DR is informative and useful for further study on PV system performance and cost of investment in tropical region. Furthermore, we are the first group in Thailand to estimate the DR of PV station at system scale based on the mixed effects method. Finally, our study has enriched the knowledge about the operation of monocrystalline silicon (Mono-Si) PV station in real operation condition. INDEX TERMSDegradation rate, Linear decline model, Levelized cost of electricity (LCOE), Mixed effects model (MEM), Mono-Si PV station.

show abstract

DC Series Arc Fault Detection and Self- Extinguishing Method With Power Stage Design of Module Level Power Electronics

Park,

Kim,

Chae

2024

IEEE Access

View full text Add to dashboard Cite

Comparative Electrical Energy Yield Performance of Micro-Inverter PV Systems Using a Machine Learning Approach Based on a Mixed-Effect Model of Real Datasets

Cited by 9 publications

References 23 publications

Application of the mixed effects model for analysing photovoltaic datasets and interpreting into meaningful insights

Application of the mixed effects model for analysing photovoltaic datasets and interpreting into meaningful insights

Annual Degradation Rate Analysis of Mono-Si Photovoltaics Systems in Thailand Using the Mixed Effects Method

DC Series Arc Fault Detection and Self- Extinguishing Method With Power Stage Design of Module Level Power Electronics

Contact Info

Product

Resources

About