Machine Learning Frameworks and Algorithms for Fog and Edge Computing

Abstract

Fog, edge and pervasive computing are technologies developed to overcome the limitations of cloud computing. In this chapter we will cover the role of various machine learning, deep learning frameworks, techniques and algorithms in fog, edge and pervasive computing. Latency, privacy, and bandwidth are some of the limitations or problems with the cloud computing and in this chapter, we will discuss how machine learning combined with these computing technologies can help to overcome the limitations of cloud computing. Inferencing is the main challenge in using machine learning or deep learning models, this chapter covers the various frameworks that help to provide inference and quantize the models. Even machine learning has some advantages and disadvantages, in this chapter we will cover the advantages and disadvantages of using machine learning in edge/fog/pervasive computing. We will also cover the various studies done by the researchers. Every field has numerous applications, in this chapter we will discuss the few possible applications in this fog era using machine learning techniques. By the end of the chapter you will know about the ML frameworks and the various machine learning algorithms used for fog/edge computing.