Dear Colleagues,

The ongoing progress in digitization and the internet of things (IoT) relies increasingly on deploying applications and services to cloud and edge infrastructures and platforms. This cloud-native focus applies equally to cloud- and edge components.

Compared to monolithic SOA-based systems, cloud-native software systems often have a much more decentralized structure and many independently deployable and (horizontally) scalable components, making it more complicated to create a shared and consolidated picture of the overall decentralized system state.

Furthermore, these systems are often developed in a DevOps-based and evolutionary design approach. Adaptations and further developments to these systems are thus carried out during the operations phase and often at the "open heart". Data-driven engineering approaches also use insights from telemetry data from the operations phase.

Nevertheless, while the current research covers the implementation of cloud-native applications and the corresponding DevOps implications, the observability of these kinds of systems is still treated somehow stepmotherly. For instance, historically, telemetry data were understood as the triad of logs, (distributed) traces, and metrics. Consequently, these kinds of data are often consolidated in specialized and isolated logging, tracing, or metric data-analysis stacks. Commonalities between these silos do exist, but they are often not used systematically and harmonized.

This Special Issue intends to address this research gap by looking for contributions in the form of systematic reviews, systematic mapping studies, product and framework reviews, benchmark performance-and-cost studies, solution proposals, case studies, and software engineering methodologies, including but not limited to:

• Collection and analysis of telemetry data of cloud- and edge software and system components;
• Consolidation of telemetry data of cloud- and edge components;
• Unification of telemetry data (logs, traces, metrics) in cloud- and edge scenarios;
• Impact of structured logging approaches on the unification and analysis of telemetry data;
• Unification of telemetry data architectures (logs, traces, metrics) in cloud- and edge scenarios;
• Black-box and white-box telemetry data acquisition;
• Managed and self-hosted telemetry data consolidation stacks;
• Telemetry data-driven SW-engineering methodologies;
• Data-science methodologies for telemetry data;
• Best practices for unified telemetry data collection in cloud- and edge scenarios;
• Telemetry data collection in different industries and use cases (cloud, edge, IoT).

Prof. Dr. Nane Kratzke
Prof. Dr. Michael Sheng
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Future Internet is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• cloud computing
• edge computing
• observability
• cloud-native
• telemetry data

Title: Cost profiling microservices applications using an APM stack
Authors: Vasilios Andrikopoulos; Sjouke de Vries; Frank Blaauw
Affiliation: University of Groningen
Abstract: Understanding how the different parts of a cloud native application contribute to its operating expenses is an important step towards optimizing this cost. However, with the adoption and rollout of microservices architectures, the gathering of the necessary data becomes much more involved and nuanced. Existing solutions for this purpose are either closed source and proprietary, or focusing only on the infrastructural footprint of the applications. In response to that, in this work we present a cost profiling solution aimed at microservices applications, building on a popular open source Application Performance Monitoring (APM) stack. By means of a case study with a data analytics development company we demonstrate how our proposed solution can provide deeper insights into the cost profile of the various application components, and drive an informed decision making in managing the application.

Title: A Deterministic Scheduler for Periodic Task Requests on Edge-Clouds
Authors: Patrick Hosein
Affiliation: Department of Computer Science, The University of the West Indies, St. Augustine, Trinidad and Tobago
Abstract: The latest cellular technology, 5G, is capable of high-throughput, low-latency transmissions making it possible to provide Edge Computing resources for a wide range of user applications as well as for real-time Smart City applications (e.g., real-time traffic control). Many of these applications require the aggregation of data from multiple sources, the processing of such data (potentially using compute intensive AI applications) and a response to a user’s application or to a controller (e.g., traffic lights). We consider the general problem in which data (potentially from multiple sources) arrives at an Edge (or Cloud) server for processing. This data arrives periodically and there is a stringent latency requirement on the response. In addition, we need to ensure that computing resources are not wasted (i.e., high computing resource utilization). We provide a deterministic scheduler for these tasks that guarantees latency requirement satisfaction, provides a high level of resource utilization and is also able to adapt to changing conditions and requirements. We use a modified version of the patented scheduler that was developed for scheduling downlink streams (Patent 11,329,760, “Method and apparatus for scheduling multimedia streams over a wireless broadcast channel” by Hosein and Gopal, issued May 2022) to achieve these objectives. We provide analytic results as well as simulation results to illustrate the benefits of this approach.