Skip to main content

Advertisement

SpringerLink
Log in

Application of Generalized Regression Neural Network in Predicting the Performance of Solar Photovoltaic Thermal Water Collector

  • Published:
Annals of Data Science Aims and scope Submit manuscript

Abstract

Solar photovoltaic thermal water collector (SPV/T-WC) is a hybrid device which converts power from the solar energy in to thermal and electrical simultaneously. The performance of such SPV/T-WC mainly depends on its electrical and thermal power output. Besides the performance of SPV/T-WC, is more sensitive to the transient nature of electrical and thermal power output. Thus a demand for predicting the performance variations in the SPV/T-WC is demand by users. Only limited performance prediction based research works are attempted in the performance prediction of the SPV/T-WC either numerically or by using cognitive models. In this study, two generalized regression neural network (GRNN) models are proposed to predict the transient performance variations in the SPV/T-WC. The two individual objectives of the first and second model include the prediction of overall power output and the overall efficiency delivered by an SPV/T-WC system. Both the GRNN models proposed in this study consist of two inputs and single output. In order to train this GRNN model, real time experiments are conducted with stand-alone SPV/T-WC for four continuous days. Then based on such experimental data sets, GRNN models are trained, tested, and validated. The results predicted by the both GRNN models are in good agreement with the real time experimental results. The overall accuracy of the proposed GRNN models in predicting the performance is 95.36% and 96.22% respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Abbreviations

PE :

Electrical power (watts)

Voc :

Open-circuit voltage (volts)

Isc :

Short-circuit current (ampere)

VL :

Load voltage (volts)

FF:

Fill factor

IL :

Load current (ampere)

G:

Irradiance (W/m2)

ηE :

Electrical efficiency (%)

APV :

PV module area (m2)

PT :

Thermal power output (watts)

M:

Mass flow rate (Kg/s)

Cp:

Specific heat of water (J/kg-K)

T1 and T2 :

Fluid inlet and outlet temperature (°C)

ΔTand dt:

Difference between Tfi & Tfo (°C)

Ta :

Ambient temperature (°C)

ηT :

Thermal efficiency (%)

AFPC :

Flat plate collector area (m2)

PO :

Overall power output (watts)

APV/T :

PV/T module area (m2)

η PV/T or ηo :

PV/T efficiency or overall efficiency (%)

AO :

Overall model accuracy (%)

Ain:

Individual accuracy (%)

er:

Error (%)

xi :

Input samples

Yi :

Output samples

Di :

Euclidean distance

n:

Number of training samples

σ:

Smoothing parameter

PV:

Photovoltaic

FPC:

Flat plate collector

SECD:

Solar energy conversion device

GRNN:

Generalized regression neural network

ANN:

Artificial neural network

PNN:

Probabilistic neural network

SPV/T-WC:

Solar photovoltaic thermal water collector

P:

GRNN input

T:

GRNN target

References

  1. Sridharan M, Jayaprakash G, Chandrasekar M, Vigneshwar P, Paramaguru S, Amarnath K (2018) Prediction of solar photovoltaic/thermal collector power output using fuzzy logic. J Sol Energy Eng 140(6):1–6

    Article  Google Scholar 

  2. Sridharan M (2020) Predicting performance of double pipe parallel and counter flow heat exchanger using fuzzy logic. ASME - Journal of Thermal Science and Engineering Applications 12(3):1–11

    Google Scholar 

  3. Sridharan M (2020) Application of generalized regression neural network in predicting the performance of natural convection solar dryer. J Sol Energy Eng 142(3):1–67

    Article  Google Scholar 

  4. Sridharan M, Jayaprakash G (2019) Verification and validation of solar photovoltaic thermal water collectors performance using fuzzy logic. ASME J Verif Valid Uncert

  5. Rizwan M, Jamil M, Kirmani S, Kothari DP (2014) Fuzzy logic based modeling and estimation of global solar energy using meteorological parameters”. Energy 70(6):685–691

    Article  Google Scholar 

  6. Ghritlahre HK, Prasad RK (2018) Development of optimal ann model to estimate the thermal performance of roughened solar air heater using two different learning algorithms. Ann Data Sci 5(3):453–467

    Article  Google Scholar 

  7. Ghritlahre HK, Prasad RK (2018) Application of ANN technique to predict the performance of solar collector systems–a review. Renew Sustain Energy Rev 84:75–88

    Article  Google Scholar 

  8. Ghritlahre HK, Prasad RK (2018) Prediction of exergetic efficiency of artificial arc shape roughened solar air heater using ANN model. Int J Heat Technol 36(3):1107–1115

    Article  Google Scholar 

  9. Ghritlahre HK, Prasad RK (2018) Exergetic performance prediction of a roughened solar air heater using artificial neural network. Strojniški vestnik J Mech Eng 64(3):195–206

    Google Scholar 

  10. Prakash O, Kumar A (2014) Application of artificial neural network for the prediction of jaggery mass during drying inside the natural convection greenhouse dryer. Int J Ambient Energy 35:186–192

    Article  Google Scholar 

  11. Bendu H, Deepak BBVL, Murugan S (2016) Application of GRNN for the prediction of performance and exhaust emissions in HCCI engine using ethanol. Energy Convers Manage 122:165–173

    Article  Google Scholar 

  12. Bendu H, Deepak BBVL, Murugan S (2017) Multi-objective optimization of ethanol fuelled HCCI engine performance using hybrid GRNN–PSO. Appl Energy 187:601–611

    Article  Google Scholar 

  13. Shi Y (2014) Big data: history, current status, and challenges going forward. Bridge US Natl Acad Eng 44(4):6–11

    Google Scholar 

  14. Sridharan M, Devi R, Dharshini CS, Bhavadarani M (2019) IoT Based performance monitoring and control in counter flow double pipe heat exchanger. Internet of Things 5:34–40

    Article  Google Scholar 

  15. Shi Y, Tian YJ, Kou G, Peng Y, Li JP (2011) Optimization based data mining: theory and applications. Springer, Berlin

    Book  Google Scholar 

  16. Qu Y, Quan P, Lei M, Shi Y (2019) Review of bankruptcy prediction using machine learning and deep learning techniques. Procedia Comput Sci 162:895–899

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Mechanical, Saranathan College of Engineering, Tiruchirappalli, Tamilnadu, 620012, India

    M. Sridharan

Authors
  1. M. Sridharan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to M. Sridharan.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sridharan, M. Application of Generalized Regression Neural Network in Predicting the Performance of Solar Photovoltaic Thermal Water Collector. Ann. Data. Sci. 10, 1–23 (2023). https://doi.org/10.1007/s40745-020-00273-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s40745-020-00273-1

Keywords

Search

Navigation