---

Introduction

INSIDER (INtelligent ServIce Deployment for advanced cloud-Edge integRation) is a research project focused on the design, analysis, and intelligent deployment of IoT applications across the edge–cloud continuum.
The project investigates methods and tools for supporting the automatic selection of suitable deployment configurations for distributed applications running on hybrid cloud/edge infrastructures.

Modern IoT applications often require low latency, scalability, privacy awareness, efficient bandwidth usage, and flexible integration across heterogeneous computing layers.
In this context, INSIDER explores how to model infrastructures and applications, define workflows and constraints, evaluate alternative deployment solutions, and support intelligent service placement decisions across cloud and edge environments.

The project adopts a platform-independent perspective, so that applications can be described first at an abstract level and then mapped onto concrete services provided by different execution environments and cloud platforms.
This enables more systematic reasoning on deployment choices and supports the development of reusable solutions for smart-city and industrial IoT scenarios.

---

Objectives

• Model hybrid cloud/edge infrastructures, services, and applications in a platform-independent way.
• Represent IoT applications as workflows of abstract services with functional and non-functional constraints.
• Evaluate alternative deployment configurations according to metrics such as latency, bandwidth, persistence, scalability, energy-related indicators, and cost.
• Support intelligent selection of deployment solutions through deterministic and AI-assisted strategies.
• Validate the proposed methodology on representative application scenarios, including smart-city and industrial IoT use cases.

---

Research Lines

INSIDER is organized around complementary research lines that connect application modeling, service discovery, deployment reasoning, and validation across the edge–cloud continuum.

• Platform-independent workflow modeling: abstraction of applications as workflows of services independent of the target provider and execution layer.
• Service composition with QoS constraints: representation of functional and non-functional requirements for intelligent deployment support.
• Deployment evaluation and selection: comparison of alternative configurations through deterministic and intelligent recommendation strategies.
• AI-assisted service recommendation: exploration of Generative AI and Large Language Models for deployment advising and multi-cloud service mapping.
• Validation on representative scenarios: assessment of the framework on smart-city and industrial IoT use cases.

---

Research Highlights

• Definition of a platform-independent methodology for designing IoT applications on the edge–cloud continuum.
• Development of software tools for workflow design, service matching, and deployment-oriented experimentation.
• Investigation of deterministic and LLM-assisted strategies for intelligent service deployment.
• Validation of the framework on smart-city mobility and industrial IoT scenarios.
• Public release of software artifacts through the official GitHub repository.
• Dissemination of the project results through international conferences, journals, public seminars, and online channels.

---

Main Results

INSIDER produced a methodological and software framework for workflow modeling, service matching, deployment advising, and deployment evaluation in heterogeneous edge–cloud environments. The project contributed to the definition of:

• a workflow-based and platform-independent modeling approach for IoT applications;
• a service recommendation and deployment-advising layer for mapping abstract services to concrete provider services;
• evaluation and selection strategies for comparing alternative deployment configurations;
• software artifacts supporting workflow design, backend solving, and execution-oriented experimentation;
• validation studies in representative smart-city and industrial IoT scenarios.

The project also contributed to the scientific discussion on intelligent deployment across heterogeneous infrastructures by combining workflow modeling, multi-cloud service reasoning, optimization-oriented approaches, and AI-assisted recommendation techniques.

---

Publications

The scientific outcomes of INSIDER have been disseminated through international conferences and journals in the areas of edge/cloud computing, IoT systems, workflow modeling, deployment optimization, and AI- and LLM-assisted data analysis and service recommendation.
The project has produced a broad portfolio of publications spanning both methodological advances and application-oriented contributions.
The complete list of publications related to the project is reported below.

1. F. Marozzo, A. Vinci, "Design of Platform-Independent IoT Applications in the Edge-Cloud Continuum". 20th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT), pp. 589-594, 2024.
2. L. Belcastro, F. Marozzo, A. Presta, D. Talia, "A Spark-based Task Allocation Solution for Machine Learning in the Edge-Cloud Continuum". 20th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT), pp. 576-582, 2024.
3. R. Cantini, C. Cosentino, F. Marozzo, "Multi-Dimensional Classification on Social Media Data for Detailed Reporting with Large Language Models". 20th International Conference on Artificial Intelligence Applications and Innovations (AIAI 2024), pp. 100--114, 2024.
4. C. Mastroianni, L. Scarcello, A. Vinci, "Quantum Computing Management of a Cloud/Edge Architecture". CF '23: Proceedings of the 20th ACM International Conference on Computing Frontiers, 2024.
5. F. Marozzo, A. Presta, R. Varchera, A. Vinci, "Estimating performances of Application Deployment on Distributed IoT-Edge-Cloud Infrastructures". 22nd IEEE International Conference on Pervasive Intelligence and Computing (PICom 2024), pp. 156-161, 2024.
6. C. Mastroianni, A. Vinci, "Tutorial on Variational Quantum Algorithms for Resource Management in Cloud/Edge Architectures". HPDC '24: Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computin, 2024.
7. L. Belcastro, F. Marozzo, A. Orsino, A. Presta, A. Vinci, "Developing Cross-Platform and Fast-Responsive Applications on the Edge-Cloud Continuum". 15th IFIP Wireless and Mobile Networking Conference (WMNC 2024), pp. 589-594, 2024.
8. L. Belcastro, F. Marozzo, A. Presta, R. Varchera, A. Vinci, "Developing Platform-Agnostic IIoT Applications in Edge-Cloud Environments". International Conference on Industry 4.0 & Smart Manufacturing 2024 (ISM 2024), vol. 253, pp. 2106-2115, 2025.
9. S. Cicero, M. Guarascio, A. Guerrieri, S. Mungari, A. Vinci, "A Deep Neural Framework for Fault Detection in IoT-Based Sensor Networks". Advances in Social Networks Analysis and Mining (ASONAM 2024), 2024.
10. C. Cosentino, M. Gunduz-Cure, F. Marozzo, S. Ozturk-Birim, "Exploiting Large Language Models for Enhanced Review Classification Explanations Through Interpretable and Multidimensional Analysis". 27th International Conference on Discovery Science (DS2024), pp. 3-18, 2024.
11. E. Cesario, P. Lindia, A. Vinci, "A scalable multi-density clustering approach to detect city hotspots in a smart city". Future Generation Computer Systems, 2024.
12. I. Khan, F. Cicirelli, E. Greco, A. Guerrieri, C. Mastroianni, L. Scarcello, G. Spezzano, A. Vinci, "Leveraging distributed AI for multi-occupancy prediction in Cognitive Buildings". Internet of Things, 2024.
13. C. Mastroianni, F. Plastina, J. Settino, A. Vinci, "Variational Quantum Algorithms for the Allocation of Resources in a Cloud/Edge Architecture". IEEE Transactions on Quantum Engineering, May 2024.
14. E. Cesario, P. Lindia, A. Vinci, "Multi-density crime predictor: an approach to forecast criminal activities in multi-density crime hotspots". Journal of Big Data, 2024.
15. L. Belcastro, C. Cosentino, F. Marozzo, A. Presta, P. Trunfio, "Empowering Efficient Drone Monitoring with Low-Latency Edge-Cloud Continuum Platforms". 33rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP 2025), pp. 333-340, 2025.
16. L. Belcastro, F. Marozzo, A. Presta, "Generative AI for Optimizing Service Mapping in the Edge-Cloud Continuum". IEEE International Conference on Pervasive Intelligence and Computing (PICom 2025), 2025.
17. L. Belcastro, C. Cosentino, F. Marozzo, M. Gunduz-Cure, S. Ozturk-Birim, "Multistakeholder Disaster Insights from Social Media Using Large Language Models". IEEE Transactions on Computational Social Systems, 2025.
18. E. Cesario, P. Lindia, F. Lobello, A. Vinci, S. Zarin, S. Capalbo, "Improving Cloud Energy Efficiency through Machine Learning Models". 33rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP), 2025.
19. G. Folino, A. Gentile, R. Varchera, A. Vinci, "Applying Multi-Objective Differential Evolution for IoT Application Design in the Edge-Cloud Continuum". GECCO '25 Companion: Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2025.
20. F. Marozzo, "Iterative Resolution of Prompt Ambiguities Using a Progressive Cutting-Search Approach". 21st International Conference on Artificial Intelligence Applications and Innovations (AIAI 2025), pp. 210-224, 2025.
21. C. Cosentino, M. Gunduz-Cure, F. Marozzo, S. Ozturk-Birim, "From Reviews to Results: Generative AI for Review-Driven Product and Service Comparisons". 28th International Conference on Discovery Science (DS2025), pp. 78–93, 2025.
22. L. Belcastro, C. Cosentino, P. Lio, F. Marozzo, "Balanced and Token-Efficient Summarization of User Reviews via Stratified Sampling and Large Language Models". European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), pp. 290–306, 2025.
23. F. Blefari, C. Cosentino, A. Furfaro, F. Marozzo, F. Pironti, "SecFlow: An Agentic LLM-Based Framework for Modular Cyberattack Analysis and Explainability". CEUR Workshop Proceedings 2025, vol. 4075, 2025.
24. L. Belcastro, F. Marozzo, A. Orsino, D. Talia, P. Trunfio, "Navigating the edge-cloud continuum: A state-of-practice survey". IEEE Access, vol. 14, pp. 40622-40647, 2026.
25. E. Cesario, P. Lindia, F. Lobello, A. Vinci, S. Capalbo, "Enhancing energy efficiency in cloud computing through regression models: A data-driven approach with experimental validation". Future Generation Computer Systems, 2025.
26. F. D Amore, L. Mariani, C. Mastroianni, F. Plastina, L. Salatino, J. Settino, A. Vinci, "Assessing projected quantum kernels for the classification of IoT data". Array, 2026.

---

Software and Repository

The main software artifacts developed within the project are publicly available through the official GitHub repository:

https://github.com/SCAlabUnical/INSIDER

The repository includes:

• a web-based workflow designer for modeling applications as compositions of abstract services;
• a backend API server supporting service recommendation and deployment-oriented solving strategies;
• example workflow specifications for representative use cases;
• Docker-based support for reproducible execution and experimentation.

The repository demonstrates that INSIDER is not limited to conceptual models, but is supported by an executable and modular software platform for workflow design, service recommendation, and deployment-oriented experimentation.

---

Events and Dissemination

INSIDER activities have been disseminated through scientific conferences, public seminars, online communication, and project meetings.
The project also promoted discussions with researchers, students, and stakeholders interested in the edge–cloud continuum, IoT applications, and intelligent deployment strategies.

Dedicated events were organized during the project lifetime to present the project goals, intermediate progress, and final results.
Dissemination activities also included online visibility through the project webpage, the public GitHub repository, and institutional/social communication channels.

---

People

The project is carried out through the collaboration of researchers from the University of Calabria (UNICAL) and ICAR-CNR.

University of Calabria (UNICAL)

UNICAL is the coordinating unit of the project and leads the activities related to project management, workflow modeling, software development, intelligent deployment support, and dissemination.

• Fabrizio Marozzo (Principal Investigator)
• Domenico Talia
• Paolo Trunfio
• Eugenio Cesario
• Cristian Cosentino
• Alessio Orsino
• Aleandro Presta

ICAR-CNR

The ICAR-CNR unit contributes to the methodological and experimental development of the project, with activities related to deployment reasoning, simulation, optimization, and validation.

• Andrea Vinci (Secondary Investigator and leader of the ICAR-CNR research unit)
• Antonio Francesco Gentile
• Gianluigi Folino
• Rosa Varchera

---

Funding Information

This project has received funding from the Italian Ministry of University and Research under the PRIN 2022 programme:

INSIDER: INtelligent ServIce Deployment for advanced cloud-Edge integRation
Grant No. 2022WWSCRR
CUP H53D23003670006

---