Dependency-Aware Resource Allocation for Serverless Functions at the Edge

Serverless computing allows developers to break their code into small components, known as functions. Being lightweight and modular, serverless functions have been increasingly employed in edge computing, where quick responses and adaptability are key to meeting strict latency requirements. In particular, edge nodes are intrinsically resourceconstrained, and efficient resource allocation strategies are crucial for optimizing their usage. Different approaches exist in the literature, but they often overlook the dependencies among functions, that is, how and when functions invoke other functions, and obtain suboptimal results. This paper presents NEPTUNE+, a dependency-aware resource (CPU cores) allocation solution for serverless functions deployed on edge infrastructures. The approach extends NEPTUNE, an existing framework for managing edge infrastructures, with a new theoretical model and control algorithm that take function dependencies into account. We evaluated NEPTUNE+ by using three applications and it is able to allocate up to 42% fewer cores compared to NEPTUNE.