Enhancing Power Conversion Efficiency in Tandem Solar Cells with Temporal Dynamic Graph Neural Network

Year : 2026 | Volume : 13 | 02 | Page :
By

Akash Nanasaheb Mahajan,

Rahul R. Bibave,

  1. Student, Department of Electrical Engineering, Sanjivani College of Engineering, Kopargaon, Maharashtra, India
  2. Assistant Professor, Department of Electrical Engineering, Sanjivani College of Engineering, Kopargaon, Maharashtra, India

Abstract

In modern homes, people want good comfort and also less electricity bill, so managing heating load and cooling load become very important. Heating Load (HL) and Cooling Load (CL) depend on many things like wall material, window size, sunlight, ventilation, and weather. Because of this many factors, calculation and optimization of HL and CL is little difficult and many time normal formulas give wrong or not perfect results. So in this study, we try to make a better and simple way to optimize energy use in houses by using GOA-PHNN approach, which is combination of Grasshopper Optimization Algorithm (GOA) and Predictive Hybrid Neural Network (PHNN). First, the basic idea of GOA come from group behavior of grasshoppers explained. This algorithm help in searching best solution in continuous optimization problems. Later many researchers improved GOA by adding chaos, adaptive rules and hybrid methods so that it converge more faster and not stuck in local area. Because of this, GOA become strong metaheuristic for building energy optimization work. In building field, many papers use neural networks and hybrid algorithms for heat load prediction. Double-target neural networks used to predict both HL and CL at the same time. Metaheuristic-optimized models give more accurate heating load estimation compare to simple machine learning models. Also ANN with different metaheuristic optimizers give early and smart analysis for energy performance of buildings. Our proposed GOA-PHNN model use GOA to tune the weights of hybrid neural network so the network learn patterns more properly. Then trained PHNN predict HL and CL for home in different conditions like room size, insulation level, outside temperature etc. In this work, GOA help to reduce error and increase efficiency of the model. After testing on building dataset, we see that GOA PHNN model give better accuracy than normal ANN and other machine learning models. In simple words, GOA find best settings and PHNN learn better, so final load prediction become more correct. This research useful for engineers, builders and homeowners to save energy, plan good insulation, and design smart buildings. Overall, the study show that GOA PHNN approach is a strong and simple method to optimize heating and cooling load in home so comfort increase and power consumption goes down.

Keywords: Heating Load Prediction, Cooling Load Prediction, Grasshopper Optimization Algorithm (GOA), Predictive Hybrid Neural Network (PHNN), Building Energy Optimization, Energy-Efficient Buildings, Artificial Intelligence, Metaheuristic Optimization.

How to cite this article: Akash Nanasaheb Mahajan, Rahul R. Bibave. Enhancing Power Conversion Efficiency in Tandem Solar Cells with Temporal Dynamic Graph Neural Network. Journal of Semiconductor Devices and Circuits. 2026; 13(02):-.
How to cite this URL: Akash Nanasaheb Mahajan, Rahul R. Bibave. Enhancing Power Conversion Efficiency in Tandem Solar Cells with Temporal Dynamic Graph Neural Network. Journal of Semiconductor Devices and Circuits. 2026; 13(02):-. Available from: https://journals.stmjournals.com/josdc/article=2026/view=251931

References

  1. Pales AF, Bennett S. Energy technology perspectives 2020. International Energy Agency. 2020:1-400.
  2. Hoxha E, Francart N, Tozan B, Stapel EB, Gummidi SR, Birgisdottir H. Spatiotemporal tracking of building materials and their related environmental impacts. Science of the Total Environment. 2024 Feb 20;912:168853.
  3. Liang Z, Chen H, Wang X, Chen S, Zhang C. Risk-based uncertainty set optimization method for energy management of hybrid AC/DC microgrids with uncertain renewable generation. IEEE Transactions on Smart Grid. 2019 Sep 6;11(2):1526-42.
  4. Fallahi F, Yildirim M, Lin J, Wang C. Predictive multi-microgrid generation maintenance: Formulation and impact on operations & resilience. IEEE Transactions on Power Systems. 2021 Apr 13;36(6):4979-91.
  5. Xie P, Jia Y, Chen H, Wu J, Cai Z. Mixed-stage energy management for decentralized microgrid cluster based on enhanced tube model predictive control. IEEE Transactions on Smart Grid. 2021 Apr 22;12(5):3780-92.
  6. Chu Z, Zhang N, Teng F. Frequency-constrained resilient scheduling of microgrid: A distributionally robust approach. IEEE Transactions on Smart Grid. 2021 Jul 7;12(6):4914- 25.
  7. Luo F, Ranzi G, Wang S, Dong ZY. Hierarchical energy management system for home microgrids. IEEE Transactions on Smart Grid. 2018 Nov 30;10(5):5536-46.
  8. MansourLakouraj M, Niaz H, Liu JJ, Siano P, Anvari-Moghaddam A. Optimal risk- constrained stochastic scheduling of microgrids with hydrogen vehicles in real-time and day-ahead markets. Journal of Cleaner Production. 2021 Oct 10;318:128452.
  9. Nikzad M, Samimi A. Integration of designing price-based demand response models into a stochastic bi-level scheduling of multiple energy carrier microgrids considering energy storage systems. Applied Energy. 2021 Jan 15;282:116163.
  10. Wu C, Gao S, Liu Y, Song TE, Han H. A model predictive control approach in microgrid considering multi-uncertainty of electric vehicles. Renewable Energy. 2021 Jan 1;163:1385- 96.
  11. Jiao F, Ji C, Zou Y, Zhang X. Tri-stage optimal dispatch for a microgrid in the presence of uncertainties introduced by EVs and PV. Applied Energy. 2021 Dec 15;304:117881.
  12. Chang R, Bai L, Hsu CH. Solar power generation prediction based on deep learning. Sustainable energy technologies and assessments. 2021 Oct 1;47:101354.
  13. Jumin E, Basaruddin FB, Yusoff YB, Latif SD, Ahmed AN. Solar radiation prediction using boosted decision tree regression model: A case study in Malaysia. Environmental Science and Pollution Research. 2021 Jun;28(21):26571-83.
  14. Li Y, Wang R, Yang Z. Optimal scheduling of isolated microgrids using automated reinforcement learning-based multi-period forecasting. IEEE Transactions on Sustainable Energy. 2021 Aug 18;13(1):159-69.
  15. Meng Q, Xi Y, Ren X, Li H, Jiang L, Yang L. Thermal energy storage air-conditioning demand response control using elman neural network prediction model. Sustainable Cities and Society. 2022 Jan 1;76:103480.
  16. Alramlawi M, Li P. Design optimization of a residential PV-battery microgrid with a detailed battery lifetime estimation model. IEEE Transactions on Industry Applications. 2020 Jan 13;56(2).
Ahead of Print Subscription Review Article
Volume 13
02
Received 25/07/2026
Accepted 02/08/2026
Published 07/08/2026
Publication Time 13 Days

Login

My IP

PlumX Metrics