Joint service placement and request scheduling at the edge

This chapter focuses on the joint allocation of multiple types of resources when trying to run machine learning applications on edge computing platforms. To have the maximum applicability, the machine learning workloads will be simply modeled as demands for various types of resources (storage, communication, computation), and the resource allocation algorithms are designed to optimally satisfy these demands within the limited resource capacities of edge clouds. Different problem formulations differ in terms of the performance objective, the types of resources considered, and the forms of resource constraints, which all originate from the different application scenarios of interest. These differences in turn lead to differences in the problem complexities and the applicable solutions.