QoS requirements for Fog Computing applications

Citation Author(s):
Judy C.
University of Campinas
Norwegian University of Science and Technology (NTNU)
University of Campinas
Submitted by:
Last updated:
Sun, 04/16/2023 - 16:24
Data Format:
Research Article Link:
0 ratings - Please login to submit your rating.


Currently, Internet applications running on mobile devices generate a massive amount of data that can be transmitted to a Cloud for processing. However, one fundamental limitation of a Cloud is the connectivity with end devices. Fog computing overcomes this limitation and supports the requirements of time-sensitive applications by distributing computation, communication, and storage services along the Cloud to Things (C2T) continuum, empowering potential new applications, such as smart cities, augmented reality (AR), and virtual reality (VR). However, the adoption of Fog-based computational resources and their integration with the Cloud introduces new challenges in resource management, which requires the implementation of new strategies to guarantee compliance with the quality of service (QoS) requirements of applications. In this context, one major question is how to map the QoS requirements of applications on Fog and Cloud resources. One possible approach is to discriminate the applications arriving at the Fog into Classes of Service (CoS). This dataset contains the QoS requirements that best characterize seven Fog applications: Mission-critical, Real-time, Interactive, Conversational, Streaming, CPU-bound, and Best-effort. Moreover, this dataset was used in the implementation of a typical machine learning classification methodology to discriminate Fog computing applications as a function of their QoS requirements.


This dataset is composed of 14,000 mutually exclusive applications generated from data in the intervals of values acceptable for each QoS requirement, following the criteria of Table 2 in our article entitled “On the classification of fog computing applications: A machine learning perspective”. Each application has nine QoS requirements, which are referred in our paper to as “attributes”: Bandwidth, Reliability, Security, Data Storage, Data location, Mobility, Scalability, Delay sensitivity, and Loss sensitivity. An independent random number generator randomly created the values of each attribute. Transient data were removed according to the Moving Average of Independent Replications procedure [Jain et al., 1991]. Attribute values were made up of safe and borderline examples. Safe examples were placed in relatively homogeneous areas concerning the class label. Borderline examples, on the other hand, are located in the area surrounding class boundaries, where different classes overlap. Also, to estimate the robustness of the classifiers, the third group of attribute values, called noisy examples, was generated. The term noisy sample refers to the samples generated to represent the corruption of their attribute values.

Funding Agency: 
CNPq-TWAS Program, CAPES, CNPq, FAPESP; FAPESP Microsoft Virtual Institute
Grant Number: 
190172/2014-2; 88881.145912/2017–01; 307560/2016-3; 2014/12236-1, 2015/24494-8, 2016/50250-1, and 2017/20945-0; 2013/50155-0, 2013/50169-1, and 2014/50715-9


how can I gate dataset

Submitted by naseem sa on Mon, 07/24/2023 - 16:45