A future smart grid must fulfil the vision of the Energy Internet in which millions of people produce their own energy from renewables in their homes, offices, and factories and share it with each other. Electric vehicles and local energy storage will be widely deployed. Internet technology will be utilised to transform the power grid into an energy-sharing inter-grid. To prepare for the future, a smart grid will not be sufficient; perhaps what we need is an intelligent grid capable of making split second decisions to ensure total generation is balanced against total demand.

​

Intelligent system with correct interface with all learning agents and control mechanisms can prioritise on renewable generation, storing electricity where necessary and dispatching quick power for instantaneous frequency response and balancing autonomously to optimise the generation and balancing mechanism better and more efficiently yet ensuring the multi-stakeholder interests within the system.

​

Hence we have argued that many of the problems posed by the transition from smart grid to an intelligent grid have long been the focus of research within the field of autonomous agents and multi-agent systems research.

​

Thus, we conclude that these tools will be essential for delivering the intelligent grid as it is envisioned. While work that has been done in this area to date represents a valuable first step, this domain represents many new challenges. Not least, we stress on the need for autonomous agents that can apply persuasive technologies and flexible autonomy in order to encourage behaviour change and coordinate energy use within the home, novel computational mechanism design approaches that effectively elicit the preferences of the user and scale to potentially millions of participants, and efficient decentralised coordination approaches that can address the full complexity of settings where non-local constraints exist.

 

For these reasons, we believe that addressing the challenge of delivering the smart grid ambitions will require an intelligent grid driven by AI based models at both micro and macro levels.