Workshop AI for Systainable Energy – CAI 2025

IEEE International Conference on Artificial Intelligence 2025 – CAI 2025

Santa Clara, California, USA, May 5-7, 2025

Organized by Zita Vale, João Soares, G. Kumar Venaygamoorthy

Energy remains the cornerstone of societal prosperity, with its production, delivery, and management critical to human advancement. As we progress into 2025, the energy field continues to transform rapidly, requiring us to broaden our approach to encompass sophisticated control, optimization, and decarbonization across increasingly complex energy systems. The urgent energy demands of growing economies persist, while our planet’s finite resources and the escalating climate crisis necessitate a sharper focus on sustainability, efficiency, and resilience. In order to navigate the multifaceted socio-economic dimensions of the energy sector, trust in AI becomes a crucial aspect. Trust is necessary to ensure that AI systems are reliable, secure, and capable of making informed decisions. Additionally, transparency and accountability are key components of trust in AI. Users and stakeholders need to have confidence in the algorithms and models used in energy systems to make fair and unbiased decisions.


Scope and Topics

Trust in AI: A Pillar of Sustainable Energy requires a robust framework of trust in AI. With rapid advancements, AI’s role brings both opportunities and risks. Ensuring AI systems are trustworthy, reliable, secure, and ethical is crucial. Transparency and accountability, bolstered by new global regulations, are key to maintaining confidence in AI-driven, fair, and unbiased decisions.

Explainability in AI: Enhancing Transparency Explainability is vital for building trust in AI systems used in energy. As AI’s influence grows in production, grid management, and consumption, it’s critical to understand how decisions are made. Recent advances in explainable AI (XAI) improve clarity, helping detect biases and inefficiencies while optimizing energy strategies.

Fairness in AI: Fairness in AI has become increasingly important in addressing energy equity. AI systems must avoid amplifying biases related to race, gender, or socioeconomic status. Fair AI design ensures equitable access to the benefits of energy AI, aligning with broader climate justice goals.

Energy Transformation: AI continues to revolutionize the energy sector with advances in machine learning, predictive analytics, and decentralized networks. AI now optimizes energy use, forecasts renewable generation, and predicts grid failures. It also supports energy trading markets and enhances the security of decentralized systems through blockchain integration.

Responsible AI: Balancing Innovation and Ethics As AI evolves, ethical considerations remain critical. Recent developments in generative AI and autonomous systems have raised questions of governance. The EU’s upcoming AI Act provides a framework for ethical AI, ensuring it aligns with sustainability and social equity. The integration of AI in energy must balance technological innovation with these ethical imperatives.

We are interested in (but not limited to) the following applications :

  • AI in autonomous control for wind and solar farms and energy resources
  • AI reduces carbon emissions by enhancing industrial processes and emissions monitoring and compliance.
  • AI in Consumer Products: this helps users directly regulate energy consumption, reducing demand and aiding power networks.
  • AI in Demand Forecasting: improves load balancing, dynamic distribution, and energy resource utilization to maximize consumer benefit and grid utility.
  • AI for Digital Twins: Real-time virtual representations of actual grid assets may be used to examine wind turbines and power plants with. Digital twins enhance energy network maintenance, experimentation, and optimization.
  • AI for Energy Communities enables fair energy trading and benefit distribution, effective energy resource management (production, storage, demand flexibility), and efficient wholesale and local energy market participation.
  • AI for Energy Consumers: it will aid energy efficiency decisions and active customer involvement in demand response programs and neighbor energy exchanges.
  • AI for Energy Efficient Industrial Plants: it promotes renewable energy consumption to make companies more sustainable and energy efficient.
  • AI for Energy Efficient Transportation: it optimizes electric car charging, routing, and interaction with the electric grid, including V2X.
  • AI for Energy Markets enables realistic energy market simulation, player decision-support, renewable energy intensive market models, and local energy market coordination.
  • AI for Oil and Gas. In upstream operations (exploration and production), AI may evaluate reservoir value, adjust drilling and completion plans to local geology, and evaluate well hazards. AI can optimize pipeline and refining scheduling, commodity and product market pricing, trading, and hedging in midstream and refining. AI saves money and boosts spreads in downstream processes.
  • AI in Plant Management reduces operation costs and carbon emissions by estimating system lifespan, predictive maintenance scheduling, and real production capacity.
  • AI to safeguard vital energy infrastructure from network access and viruses.
  • AI for Sensor Fusion, which transforms data from hundreds to millions of sensors for better city, state, and national tracking and decision-making.
  • AI in Smart Grid Operation, Control, and Management to predict outages, maximize power yield, and improve demand-side management to reduce energy demand peaks. Smart Grid optimizes power flow for economic efficiency, dependability, and sustainability by allowing providers and consumers to exchange power and data.
  • AI in Transition to Renewables provides real-time power grid monitoring, precise power fluctuations forecasts, and novel geothermal energy solutions.
  • AI for Sustainability and the Environment. Most of the past applications of this sector focused on normal AI applications to energy, but AI can minimize energy use. Massive language model training (AI energy use), data center energy utilization, etc.

Deadlines for submitting papers to Workshop in CAI 2025:

Paper submission due: 15 January 2025. 
Acceptance notification: 1 March 2025.
Camera Ready: 7 March 2025.

How to submit the paper to the workshop

Kindly submit your paper through the main conference system, but select our Workshop AI for Sustainable Energy.

If you have any questions related to this workshop, kindly send mail to G. Kumar Vennaygamoorthy (gkumar@ieee.org), Zita Vale (zav@isep.ipp.pt), and Joao Soares (jan@isep.ipp.pt). Please include all the co-organizers in your e-mail communications.


Organizers

Zita Vale
Zita Vale – Polytechnic of Porto
João Soares – Polytechnic of Porto
G. Kumar Venaygamoorthy – Clemson University