Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM62422
Volume:
10 |
5 |
May 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of CSE
College of Engineering , Kidangoor
Department of CSE
College of Engineering , Kidangoor
Department of CSE
College of Engineering , Kidangoor
Department of CSE
College of Engineering , Kidangoor
Department of CSE
College of Engineering , Kidangoor
Abstract—The rapid proliferation of distributed solar energy systems has created a pressing need for decentralized platforms enabling direct energy exchange among households. This paper presents an AI-driven peer-to-peer (P2P) renewable energy trading system built on blockchain technology. The platform enables prosumers—households that both generate and consume electricity—to trade surplus solar energy using Solidity smart contracts deployed on the Polygon network, eliminating the need for centralized intermediaries. A bidirectional Long Short-Term Memory (LSTM) neural network provides short-term forecasting of energy generation and consumption, empowering users with AI-driven trading recommendations. The system architecture integrates five modular components: a Python-based energy simulation engine supporting up to eight household profiles, an LSTM and regression-based AI forecasting module, a Django REST Framework backend for data management and marketplace logic, Solidity smart contracts for transparent on-chain trade execution, and a React (Vite) real-time dashboard for user interaction. The platform incorporates an off-chain token wallet system with CO2 savings tracking and supports real-time data synchronization via Firebase. Testing demonstrates successful end-to-end P2P energy trades, accurate energy predictions, and a responsive marketplace interface. The system contributes to the growing body of decentralized energy research by delivering an open-source, full-stack implementation that addresses transparency, trust, and intelligent decision-making in residential energy trading.
KEYWORDS
AI predictions for informed decision-making. The physics-based simulation model (Eqs. 1–8) generates realistic household energy data, the bidirectional LSTM model (Eqs. 11–16) provides accurate short-term forecasting, and the CO2 tracking mechanism (Eq. 9) quantifies environmental impact. The off-chain token wallet combined with on-chain trading provides a practical balance between decentralization and usability. Future work will focus on several enhancements: (1) deploying the smart contracts on the Polygon mainnet for realworld testing; (2) implementing transformer-based forecasting architectures for improved prediction accuracy; (3) adding game-theoretic dynamic pricing algorithms based on real-time supply-demand ratios; (4) integrating IoT smart meters for direct household energy data acquisition; (5) expanding the platform to support vehicle-to-grid (V2G) energy trading with electric vehicles; and (6) conducting large-scale pilot studies with real prosumer communities to validate the system under production conditions.
[1] Debut Infotech, “Why blockchain in P2P energy trading is shaping renewable energy’s future,” Jan. 2026. [Online]. Available: https://www. debutinfotech.com/blog/blockchain-for-p2p-energy-trading [2] W. Tushar, C. Yuen, H. Mohsenian-Rad, T. Saha, H. V. Poor, and K. L. Wood, “Transformations in peer-to-peer prosumer energy networks,” IEEE Signal Process. Mag., vol. 35, no. 4, pp. 81–99, 2018. [3] W. Tushar, T. K. Saha, C. Yuen, D. Smith, and H. V. Poor, “Peer-to-peer trading in electricity networks: An overview,” IEEE Trans. Smart Grid, vol. 11, no. 4, pp. 3185–3200, 2020. [4] O. Adeyemi et al., “Blockchain-based P2P renewable energy trading and traceability of transmission and distribution losses,” J. Oper. Res. Soc., vol. 77, no. 1, 2026. [5] M. Andoni et al., “Blockchain technology in the energy sector: A systematic review of challenges and opportunities,” Renew. Sustain. Energy Rev., vol. 100, pp. 143–174, 2019. [6] N. Szabo, “Smart contracts: Building blocks for digital markets,” Extropy J., 1996. [7] M. Abdel-Nasser and K. Mahmoud, “Accurate photovoltaic power forecasting models using deep LSTM-RNN,” Neural Comput. Appl., vol. 31, pp. 2727–2740, 2019. [8] A. Zameer, F. Jaffar, F. Shahid, M. Muneeb, R. Khan, and R. Nasir, “Short-term solar energy forecasting: Integrated computational intelligence of LSTMs and GRU,” PLoS ONE, vol. 18, no. 10, e0285410, 2023. [9] M. F. Zia et al., “Decentralized P2P energy trading in microgrids: Leveraging blockchain technology and smart contracts,” Energy Rep., vol. 10, 2024. [10] E. Mengelkamp, J. Garttner, K. Rock, S. Kessler, L. Orsini, and¨ C. Weinhardt, “Designing microgrid energy markets: A case study: The Brooklyn Microgrid,” Appl. Energy, vol. 210, pp. 870–880, 2018.
Publication Date
5/3/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
7
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...