The purpose of the International Workshop on AI Empowers the Smart Grid (AIPower) is to bring together researchers from different fields of AI and practitioners interested in the advances and applications of AI techniques in the field of Smart Grids (SGs), especially when considering the empowerment of users in SGs.

The convergence of information technologies and energy "utilities" is the source of many scientific challenges beyond communication technologies and energy management, notably Artificial Intelligence. Indeed, the intelligent management of electrical networks which handle energy and data could be at the origin of many societal and environmental gains, particularly in terms of CO2 emissions, energy waste and user empowerment. This "intelligence" must go beyond the technologies currently in place for the design and control of conventional energy networks. Information and communication technologies enable individuals’ communication within energy networks, but are far from exploiting their collaborative potential. Despite the recent surge of interest in technologies to help individuals collaborate, such as energy markets, these are still in its infancy. And yet, such technologies are core to enable future smart infrastructures for the citizens. Indeed, participation and social innovation are at the heart of the development of the SGs, which require intensive collaboration within collectives.

The increasingly numerous and fine-grained data on appliance profiles, user profiles, or status of various components of the electrical network, and the massive deployment of controllable and monitorable smart devices (such as smart meters, smart plugs, or phase measurement units) are all opportunities, but also challenges to be intelligently integrated, to implement SGs and empower their users. We target novel technologies that empower human collectives to operate SGs to achieve sustainable energy management by supporting their self-awareness, cooperation, and self-governance. We think in particular, but not exclusively, to machine learning techniques (e.g. to model user profiles, to determine price-fixing policies), resource allocation (e.g. for optimal energy dispatch, to define distributed energy markets), knowledge representation (e.g. to install system interoperability, to automate reasoning and network diagnostic), complex event processing (e.g. to provide more flexible control for energy-aware users and demand-response management systems), coordination and social computing (e.g. to form energy prosumer communities to to agree on the rules to employ to allocate energy) or game theory (e.g. cooperative and non-cooperative resource allocation), or gamification techniques (e.g. to educate community prosumers so that they learn efficient energy management practices). The distributed, decentralized and uncertain nature of activities in SGs also makes agent and multiagent approaches, in conjunction with the aforementioned AI techniques, promising paradigms for providing both theoretical and practical solutions for empowering SGs.

Papers describing the use of such AI techniques and technologies for empowerment in SGs, or demonstrating how SGs concerns may raise scientific challenges for AI techniques and theories are welcome. Papers expounding innovative prototypes, systems and tools, and general survey papers indicating future directions are also encouraged. Papers describing original work are invited in any of the areas listed below. There will be both oral and poster presentations.