IJCNN banner

Workshop: Deep Learning Techniques for Observable Smart Grid and Sustainable Energy Systems

International Joint Conference on Neural Networks (IJCNN) 2025

4th July 2025, Rome, Italy

Supported by IEEE CIS Task Force on Computational Intelligence in the Energy Domain

Overview

The global energy landscape stands at a critical juncture, shaped by the dual pressures of climate change and surging energy demand. As we navigate these complex issues, developing smart grid observability methodologies has emerged as a pivotal challenge. Smart grids have rapidly evolved into the backbone of modern energy infrastructure, revolutionizing the interaction between renewable energy sources, traditional power generation, and the ever-changing needs of consumers. This technological revolution has not only transformed how we generate and distribute energy but has also redefined the very nature of energy consumption. Central to this transformation is the role of data analytics and advanced neural network techniques. Advanced metering Infrastructure provides extensive data on energy usage, offering insights that extend far beyond simple meter readings. This wealth of information unlocks the potential for nuanced consumer demand profiling, precise load forecasting, and optimized renewable energy integration. However, as smart grids become increasingly sophisticated, incorporating everything from photovoltaics (PVs) to electric vehicle (EV) charging, the need for advanced neural network methods to monitor, analyze, and optimize these systems has never been more pressing. At the same time, this new energy paradigm, characterized by increasingly distributed energy sources and a diversifying consumer base amplifies the complexity of the grid. This evolution demands enhanced situational awareness in contemporary energy systems. As distributed generation, energy storage solutions, and renewable energy sources are progressively integrated into the grid, they improve power supply capabilities while simultaneously introducing novel consumption patterns and exerting unprecedented pressures on existing power systems. This necessitates network infrastructures that offer improved observability, accessibility, and controllability, underpinned by distributed intelligence systems.

The extraction of useful information, such as load profiles, power quality, energy consumption, and generation patterns, becomes a key component of energy systems, where electrical signal processing and computational intelligence techniques play a key role. Advanced artificial neural network techniques can improve the performance and accuracy of these methods, by providing adaptive, robust, and scalable solutions to the challenges posed by the Smart Grid.

This workshop offers an opportunity for researchers from various research fields, such as machine learning, artificial neural networks, power and energy systems, communications, optimization, and control engineering, to share their insights on how neural network techniques can enhance observability and electrical signal processing for Smart Grids and Sustainable Energy Systems.

The workshop is supported by the Computational Intelligence for Energy (CI4Energy) task force (CIS-TF3).

Topics covered

The topics of interest include but are not limited to computational intelligence techniques applied in:

Submission Guideline

Please follow the submission guideline from the IJCNN 2025 Submission Website. Workshop papers are treated the same as regular conference papers.

Important Dates

Sponsorship Possibilities

We are offering sponsorship opportunities to various organizations eager to showcase its commitment to advancing the field of artificial intelligence, support the workshop, and gain visibility among prominent researchers, engineers and students. For more information, visit our Sponsorship Page.

Organizers