The Role Of Artificial Intelligence In Smart Utilities

A Japanese construction firm claims to have developed a smart energy system powered by artificial intelligence to manage its solar power plant. The system, which is called AHSES (short for “Adjusting to Human Smart Energy System”) is used to anticipate, manage, and display energy needs from the solar power plant. Much like AI systems in other industries, the power plant uses machine learning and mathematical methods. More importantly, it supports smart pricing. It also kicks in during emergencies to ensure that critical parts of the system, such as servers, are functional. Finally, the system can be expanded or downsized based on needs. 

This is not the first time that artificial intelligence is being used in the electric utility industry. A Swiss company called Alpiq developed an intelligent system called GridSense to “gauge, learn, and anticipate” user behavior for intelligent energy management. Given rapid strides in the technology, artificial intelligence will become an integral part of the energy industry in the future. 

Part of the reason for this is that the industry’s complexity will become difficult to manage as it decentralizes and moves towards a decentralized smart grid-based system. From boiler plants to distribution pipelines and grids, the industry consists of several moving parts. The transition towards dynamic demand management and smart pricing will produce mountains of data that will be impossible to manage and analyze without the help of machine learning.  

AI is already being used in various industries for similar purposes. For example, it is used to design search algorithms, messaging bots, as well as home assistants. Alphabet Inc. subsidiary Google claims to have shaved off costs from its electric bill by using artificial intelligence to manage electricity demand for its data centers. 

A 2016 paper by consulting firm Deloitte LP outlines additional uses for AI technology in the utility industry. The list includes deployment of devices, such as smart meters, and combining them with advanced analytics to “enable sophisticated decision making and problem solving in real-time.” It can also be used to control drones and robotic devices to inspect and maintain distribution systems.