A Sparse Function Prediction Approach for Cold Start Optimization and User Satisfaction Guarantee in Serverless

Serverless computing relies on keeping functions alive or pre-warming them before invocation to mitigate the cold start problem, stemming from the overhead of initializing function startup environments. However, under constrained cloud resources, accurately predicting the invocation patterns of sparse functions remains challenging. This limits the formulation of effective pre-warm and keep-alive strategies, leading to frequent cold starts and degraded user satisfaction. To address these challenges, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SPFaaS</i>, a hybrid framework based on sparse function prediction. To enhance the learnability of sparse function invocation data, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SPFaaS</i> takes into account the characteristics of cloud service workloads along with the features of pre-warm and keep-alive strategies, transforming function invocation records into probabilistic data. It captures the underlying periodicity and temporal dependencies in the data through multiple rounds of sampling and the combined use of Gated Recurrent Units and Temporal Convolutional Networks for accurate prediction. Based on the final prediction outcome and real-time system states, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SPFaaS</i> determines adaptive pre-warm and keep-alive strategies for each function. Experiments conducted on two real-world serverless clusters demonstrate that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SPFaaS</i> outperforms state-of-the-art methods in reducing cold starts and improving user satisfaction.