Optimizing Tyre and Brake Performance in Formula 1 Using Big Data Analytics: A Survey on Predictive Models and Strategies

Two of the most important components influencing both performance and safety in Formula One (F1) racing, where milliseconds define success and failure are tyres and brakes. These components withstand particularly difficult conditions, which can lead to issues including brake fade and tyre degradation that significantly influences the race outcome. Notwithstanding technological improvements, it is still difficult to project exactly how these components should be kept and used. This is important considering the massive amounts of telemetry data generated during events and practices. The use of big data analytics is discussed in this work in order to grasp and enhance Formula One brake and tyre performance. Real-time processing and telemetry data interpretation including measures of tyre pressure, temperature, wear levels, and brake disc temperatures is the main challenge to be solved. This comprehensive review of machine learning algorithms highlights under a range of race conditions the value of regression analysis, clustering, and decision trees in forecasting ideal tyre change strategies and brake cooling requirements. The methodology of the survey combines published works analysis, industry reports, and technical documentation for Formula One. This paper attempts to identify the most recent developments in data-driven models for application in motorsports together with their limitations. Predictive analytics lets the results of past studies show potential for better lap times, longer tyre lifetime, and more efficient brake cooling systems. Moreover, discussed in the paper is the application of real-time analytics into race strategies, so enabling teams to make informed decisions balancing performance with safety. Those engineers, data scientists, Formula One strategists ready to use big data to get a competitive advantage will much value the insights this survey provides. Furthermore, under research are potential future directions including hybrid prediction models and advanced neural networks integration.