A blockchain-secured multi-agent GNN–XGBoost framework for intelligent energy coordination in IoT-enabled sustainable smart grids

Abstract The increasing deployment of distributed energy resources and intelligent devices has transformed conventional power networks into highly decentralized smart grid ecosystems. While this evolution offers significant opportunities for improving energy efficiency and sustainability, it also introduces challenges related to real-time energy coordination, dynamic load balancing, secure data exchange, and adaptive decision-making. Traditional energy management approaches often struggle to capture complex interactions among interconnected grid components and are limited in their ability to respond effectively to rapidly changing operating conditions. To address these challenges, this paper presents an intelligent energy management framework that integrates Internet of Things (IoT) technologies, blockchain-enabled security, multi-agent coordination, Graph Neural Networks (GNNs), and XGBoost-based predictive analytics. In the proposed architecture, distributed agents representing energy producers, consumers, and prosumers collaborate to monitor grid conditions and exchange operational information. The GNN module learns structural relationships among interconnected nodes, enabling a comprehensive understanding of network dynamics. Based on the extracted graph representations, the XGBoost model supports efficient decision-making for energy dispatch, demand response, and load distribution. A blockchain layer is incorporated to ensure data integrity, transparency, and trust among participating entities without relying on centralized control. The proposed framework is evaluated in a smart city energy environment using integrated simulation and edge-computing platforms. Experimental analysis demonstrates its capability to improve energy coordination, enhance system adaptability, reduce transmission inefficiencies, and support secure decentralized operation. The findings indicate that the proposed approach provides a reliable and scalable solution for sustainable smart grid management, contributing to the development of resilient and energy-efficient urban infrastructures.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-12
DOI
https://doi.org/10.1038/s41598-026-73849-1
Primary Topic
Smart Grid Energy Management
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A blockchain-secured multi-agent GNN–XGBoost framework for intelligent energy coordination in IoT-enabled sustainable smart grids

Baddu Naik Bhukya, Samanthaka Mani Kuchibhatla, Ravi Kumar Munaganuri, Venkataiah Vaadaala et al.
Scientific Reports
Smart Grid Energy Management
article

A blockchain-secured multi-agent GNN–XGBoost framework for intelligent energy coordination in IoT-enabled sustainable smart grids

Baddu Naik Bhukya, Samanthaka Mani Kuchibhatla, Ravi Kumar Munaganuri, Venkataiah Vaadaala, Siva Kumar Kommerla
article en

Abstract

Abstract The increasing deployment of distributed energy resources and intelligent devices has transformed conventional power networks into highly decentralized smart grid ecosystems. While this evolution offers significant opportunities for improving energy efficiency and sustainability, it also introduces challenges related to real-time energy coordination, dynamic load balancing, secure data exchange, and adaptive decision-making. Traditional energy management approaches often struggle to capture complex interactions among interconnected grid components and are limited in their ability to respond effectively to rapidly changing operating conditions. To address these challenges, this paper presents an intelligent energy management framework that integrates Internet of Things (IoT) technologies, blockchain-enabled security, multi-agent coordination, Graph Neural Networks (GNNs), and XGBoost-based predictive analytics. In the proposed architecture, distributed agents representing energy producers, consumers, and prosumers collaborate to monitor grid conditions and exchange operational information. The GNN module learns structural relationships among interconnected nodes, enabling a comprehensive understanding of network dynamics. Based on the extracted graph representations, the XGBoost model supports efficient decision-making for energy dispatch, demand response, and load distribution. A blockchain layer is incorporated to ensure data integrity, transparency, and trust among participating entities without relying on centralized control. The proposed framework is evaluated in a smart city energy environment using integrated simulation and edge-computing platforms. Experimental analysis demonstrates its capability to improve energy coordination, enhance system adaptability, reduce transmission inefficiencies, and support secure decentralized operation. The findings indicate that the proposed approach provides a reliable and scalable solution for sustainable smart grid management, contributing to the development of resilient and energy-efficient urban infrastructures.

Scientific Reports
VIT-AP University (IN), Prasad V. Potluri Siddhartha Institute of Technology (IN), Koneru Lakshmaiah Education Foundation (IN)
Affordable and clean energy, Industry, innovation and infrastructure
Smart Grid Energy Management
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon