AI powers electrical grids that allow two-way communication between utilities and consumers. Smart grids are embedded with an information layer that allows communication between its various components so they can better respond to quick changes in energy demand or urgent situations.
The world is moving towards digitisation. A lot of us across the world are working from home and attending meetings via Zoom, Teams, Slack , Yammer, and WhatsApp video calls. The pandemic has reinforced the value of digitisation in our lives and compelled the uninitiated to quickly learn the new skills for staying relevant and useful for their business. Keeping in line with this trend, a lot of verticals in the economy are moving to upcoming technologies like Data Analytics, Artificial Intelligence, Internet of Things, etc. One of these verticals is the power sector.
Artificial intelligence (AI) has the potential to cut energy waste, lower costs, and accelerate the use of clean renewable energy sources in power grids globally, along with improving the operation, maintenance, control, planning and plan execution of power systems. AI is thus closely tied to renewable, clean as well as affordable energy that is necessary for development. The power sector has a bright future with the advent of AI-managed smart grids if implemented well. In addition, AI brings the customer back in focus by connecting power generators, gird managers and end consumers to be connected and served efficiently and better. It must also be stated that AI is also employed to reduce the environmental impacts from thermal power plants, improve their performance and thus play a more efficient role in supplying power to the grid.
AI powers electrical grids that allow two-way communication between utilities and consumers. Smart grids are embedded with an information layer that allows communication between its various components so they can better respond to quick changes in energy demand or urgent situations. This information layer, created through widespread installation of smart meters and sensors, allows for data collection, storage, and analysis. Given the large volume and diverse structure of such data sets, techniques such as machine learning, Internet of Things, etc are best suited for their analysis and use. This analysis can be used for a variety of purposes, including seamless fault detection in meters, predictive maintenance needs, quality monitoring of sustainable energy, as well as renewable energy forecasting, along with latest innovation in Information and Communications technology (ICT). The power sector in developed countries has already started using AI, Data Analytics, Internet of Things (IoT), and related technologies that allow for communication between smart grids, smart meters, and computer devices. These technologies help prevent power mismanagement, inefficiency, and lack of transparency, while increasing the use of renewable energy sources. As per NITI Ayog’s report National Strategy for Artificial Intelligence, many industries are proactively investing in cognitive and AI solutions, with global investments expected to achieve a compound annual growth rate of 50.1% reaching $57.6 billion in 2021. India can also learn from markets such as the USA, where consumers can choose their energy providers, based on their household budget, or their consumption patterns. To increase AI efficiency, researchers at Carnegie Mellon University, USA have developed a machine learning system called “Lumator” that combines the customer’s preferences and consumption data, along with information on the different tariff plans, limited-time discount rates, and other offers to provide recommendations for most suitable electricity supply set-up.
The pandemic has not only compelled everyone to work remotely but made us a lot more environmentally cautious. These developments are also pushing petroleum companies to pivot to new ways of working, making digital technology adoption critical. Battery storage
backed by AI is gaining traction. Excess solar or wind power is stored in these batteries during less demand times and used when energy demand is high. As a result, AI can improve reliability of solar and wind power by analysing enormous amounts of meteorological data regarding solar intensity and using this information to make predictions and decisions about when to gather, store, and distribute wind or solar power. In addition, AI is also used in smart grids to help balance the grid with respect to energy supply. This technology analyses the grid before and after intermittent units are absorbed and learns from this to help reduce congestion and energy curtailment. Smart devices such as Amazon Alexa and Google Home enable customers to directly interact with their control systems like thermostats, etc to monitor their energy consumption. Also, energy management and consumer appliances will allow automatic meters at home to use AI to optimize energy consumption and storage.
This technology can also be used to spot discrepancies in usage patterns if any, payment history of the consumer, and other data to detect any inefficiency or lack of transparency. It can also help to optimize costly and time-consuming physical inspections. The customer will face less of red-tape, and errors due to manual data entry. The need for interconnection has given rise to the industrial internet of things (IIoT), technology of a new era that works on and extends the impact of digital technology.
Despite the extensive potential of AI in energy, there are many issues which need to be addressed, namely:
· Maintaining a balance between digitisation and cyber security. Oil and gas have tremendous geo-political and economic significance, which makes them more vulnerable to cyber-attacks. A report by IBM Security revealed that the average total cost of a data breach fell to $3.86 million in 2020 alone. The world’s first successful attack of this kind happened in Ukraine during 2015, leaving many without power.
· Lack of appropriate data in AI, capacity to integrate different data sources, and to ensure all representatives in the database are taken into consideration is challenging.
· India lacks an inter- industry and inter-industrial collaboration, which makes it difficult for any concrete plan in data privacy to effectively be implemented. Internationally, UAE has created a “Ministry of Artificial Intelligence”, and “Artificial Intelligence Council” (U.K). China, USA, France, and Japan have committed a significant public spending for AI. India can pick and choose what suits the domestic demands.
· There is also an issue with aging infrastructure that is outdated, requires huge investments, and often suffers from intermittent digital connectivity. This issue is fairly common in India, where electricity supply is not linear.
· Lack of research funds is another major handicap. As per NITI Ayog, India had 2.6 million STEM graduates in 2016. Disappointingly, most of them get into regular IT jobs, and not research. At the same time, AI companies have expertise in maths and computer science, but they often lack the insight needed to understand the details of power systems.
· The excessive reliance on mobile phone technology limits AI’s potential in rural and underserved areas in many emerging markets, particularly in low-income countries.
· AI-based models are essentially unknown to most of their users, the majority of whom do not understand their working, or how they were developed, which constitutes a major security risk. Like other sectors that are increasingly relying on AI technology, the power sector will also have to address challenges such as governance, transparency, security, safety, privacy, and economic impact.
Recognising the potential of digitisation, the government has initiated macro projects such as digital India, smart cities etc. However, a lot needs to be done to secure the 5 pillars of AI, namely, policy makers, large companies, start-ups, universities, and multi-stakeholder partnerships. Once these are secured, we will be on the right path to securing AI in the energy sector.
Source: businessworld.in
