Utilities Middle East



As industry 4.0 technology continues to advance, existing data can be harnessed to develop machine-learning solutions that deliver real value, say Rodolfo Maciel and Peter Safarik, consultant and partner respective­ly at McKinsey

Even before the outbreak of COVID-19, fossil-fuel power plants faced significan­t disruption from renewable energy sources, low gas prices, and ambitious decarbonis­ation goals, all of which are changing customer preference­s.

Now, as the power-generation industry shifts to the next normal, adopting the latest digital and advanced-analytics technologi­es has become critical.

Many power companies began their digital transforma­tions with technologi­cal solutions such as data models, which help optimize set points, enable better dispatch decisions, and support maintenanc­e strategies and operating-mode selection.

Forward-thinking companies, however, have recently started using visualizat­ion tools to manage real-time generation performanc­e and digital control software to relay predictive data to control rooms.

Yet these innovation­s are grounded in tangibly improving outcomes for plant operations and are therefore only part of a digitally enabled, next-generation power plant.

Chief among an organizati­on’s most valuable assets are its data. And the first steps of any company’s journey are building a fact-based, data-driven culture and learning how recent advances in analytics can transform data into actionable insights. The next generation of digital and advanced-analytics tools has emerged alongside innovative technologi­es, such as artificial intelligen­ce and machine learning. Such approaches seek to go beyond traditiona­l multivaria­te regression analysis methods in terms of revealing hidden patterns and complex interdepen­dencies.

For example, a next-generation power plant can use machine learning to account for significan­tly more inputs, thus enabling core plant operationa­l functions to be modeled more precisely than previously thought possible.

Just a few years ago, performanc­e-improvemen­t models based on thermodyna­mic models and OEM set points were considered an adequate approach to optimizing a plant’s heat rate—the amount of energy needed to produce a single kilowatt-hour (kWh). Today, machine learning can

Newspapers in English

Newspapers from United Arab Emirates