Projects
Intelligent Orchestration for the Compute Continuum
This project focuses on developing intelligent, adaptive orchestration mechanisms for the emerging cloud-edge-IoT compute continuum, where applications must operate across highly heterogeneous and distributed infrastructures. The research introduces novel AI-driven approaches for autonomous workload management, including the Distributed Adaptive Cloud Continuum Architecture (DACCA) and the Distributed and Adaptive Resource Optimization (DARO) framework, which leverages multi-agent reinforcement learning for decentralized and cooperative scheduling. To support the training and evaluation of intelligent schedulers, the project also developed KWEST, a high-fidelity Kubernetes workload simulator that enables realistic, reproducible experimentation across diverse cluster configurations and workload conditions. The developed technologies aim to overcome the limitations of traditional centralized orchestration systems by enabling self-aware, resilient, and resource-efficient management of next-generation distributed applications across the entire compute continuum.
Storage Data Flow Management based on Machine Learning
Hybrid data storage systems, if used effectively, can be instrumental in meeting the growing data storage and I/O demands of modern large-scale data analytics and HPC workloads. However, the complexity of data movement across storage tiers and caches increases significantly, making it harder for applications to take advantage of the system's higher I/O performance. The general objective of the SMML project is to automate data flow management for caching and storage tiering in hybrid data storage solutions, leveraging newly developed artificial intelligence algorithms to achieve an optimal performance-to-cost ratio across different storage media capacities. The proposed methodology combines mathematical modeling with streaming machine learning for the first time to guide decisions in data storage systems. The expected outcome of the project will be instrumental in meeting the increasing data storage and I/O demands of modern large-scale data analytics and high-performance computing workloads, as it could offer sustainable high performance with lower cost. This project is carried out in collaboration with Huawei Research.
Smart Cloud Caching for Data Intensive Applications
As Cloud computing is gaining popularity among small and medium enterprises, Cloud storage solutions such as Amazon S3 are increasingly used to store, manage, and serve application data. Despite the typical high-speed internet connections between applications and Cloud storage, there is still a huge performance gap compared to accessing data from direct-attached memory or even locally attached disks. SMACC is a novel Cloud caching service developed at CUT that can run on application compute nodes (e.g., on Amazon EC2) and cache frequently used data residing on cloud storage (e.g., Amazon S3, MinIO) in local memory and locally attached disks (e.g., Amazon EBS) using new smart policies. SMACC also provides an HDFS-compatible API that can be used by big data platforms such as Spark and Hadoop to process data stored on Amazon S3, caching data blocks on various compute nodes to improve performance.
Smart Edge Services for the Port Continuum
The SmartPort project develops a cloud-edge-IoT continuum platform to support the digital transformation of modern container terminals and advance the Port 4.0 vision. The project addresses key operational challenges in seaports, including equipment downtime, inefficient maintenance practices, and labor-intensive inspection processes, by integrating artificial intelligence, edge computing, and IoT technologies. Machine learning models are developed for predictive maintenance of container-handling equipment, enabling early fault detection and improved operational reliability. In parallel, deep learning-based computer vision solutions are introduced for real-time container tracking and automated damage detection during terminal operations. By combining intelligent monitoring, predictive analytics, and automated inspection capabilities, the project aims to enhance port efficiency, safety, and resilience while enabling more sustainable and data-driven management of future smart ports.
Computational Intelligence Approaches for Optimizing Seaside Operations in Smart Ports
The increasing number of ships and containers observed in recent decades poses several challenges for marine container terminals (MCTs), including congestion, long waiting times before ships dock, delayed departures, and high service costs. The berth allocation problem (BAP) and the quay crane assignment problem (QCAP) are two of the most important optimization problems in container terminals at ports worldwide. The CIBAP project develops several computational intelligence (CI)- based methodologies for various BAP formulations in real-world environments with practical constraints. The first formulation considers the stand-alone BAP with the objective of reducing the total service cost. We extend the study of BAP to multiple quays, adding the dimension of assigning a preferred quay to each arriving ship, rather than just specifying the berthing position and time. Eventually, this project investigates multi-quay combined BAP and QCAP, and solves it using CI approaches. For all formulations, a mathematical model is developed, and each problem is formulated as a mixed-integer linear programming (MILP) model. Since BAP (and its variations) is an NP-hard problem, a metaheuristic approach, namely, a cuckoo search algorithm (CSA), is proposed to solve the BAP. To validate the performance of the proposed CSA-based method, we use two benchmark CI approaches, namely, the genetic algorithm (GA) and particle swarm optimization (PSO). The comparative analysis and experimental results show that the CSA-based method outperforms other CI-based methods and achieves near-optimal performance in a reasonable time across all considered scenarios.
Intelligent Vessel Monitoring with AIS
The Automatic Identification System (AIS) is an automatic tracking system used on ships and by Vessel Traffic Services (VTS) for monitoring vessel movements in real time. AIS signals are sent in regular intervals containing encoded information regarding a vessel, including its unique identification, position coordinates, speed, and course over ground, next port destination, and many more. The CUT-AIS Ship Tracking Intelligence Platform is a web-based platform that leverages AIS data to provide meaningful visualizations, graphs, and analytics for the end user. The platform consumes data in real time from three sources: (i) a base station consisting of a VHF antenna, a receiver, and a Raspberry Pi installed in the premises of CUT; (ii) an AIS stream provided by the Cyprus Shipping Deputy Ministry; and (iii) base stations operated by Tototheo Maritime around the coast of Cyprus. AISafety is another web-based platform for monitoring and visualizing ship traffic in the Eastern Mediterranean Sea using AIS data. The key feature of the platform is generating real-time, valid warnings for incoming and outgoing ships across various areas of interest, as well as for potential ship collisions. Finally, in the AISAI project, AIS data is utilized to train (i) machine learning models that provide accurate, dynamic ETA predictions and (ii) deep learning-based sequence models to forecast vessel trajectories over short and long horizons, supporting proactive traffic management, navigational safety, and operational planning.
Environmental Quality Monitoring & Analysis
CUT Environmental Monitoring is an intelligence platform that is developed and maintained by DICL in collaboration with Dr. Michalis P. Michaelides from Cyprus University of Technology and enables users to access, extract, and analyze air quality, water quality, and meteorological data. Data can be viewed or extracted via a table dashboard, where users can request specific data they are interested in. Moreover, these data can also be viewed through our user-friendly live map. Finally, the platform provides a set of various graphs that present key statistics regarding the collected data. Overall, the CUT Environmental Monitoring platform enables end users to monitor parameters related to air and water pollution.
AI-Driven Smart Tourism Analytics and Decision Support Systems
The SmartTourism project investigates how artificial intelligence, big data analytics, and explainable machine learning can support the development of smarter and more personalized tourism services. By analyzing tourists’ electronic word of mouth (eWOM) from online review platforms, the research extracts insights into visitor experiences, preferences, satisfaction, and behavioral intentions. Machine learning models are developed to identify factors influencing tourist satisfaction and revisit intention, enabling tourism organizations to design targeted marketing strategies and improve service quality. In addition, the project introduces personalized recommendation approaches that integrate customer preferences, opinions, and personality traits to enhance the accuracy of tourism service recommendations. The developed AI-driven methods provide valuable decision-support capabilities for destination managers and hospitality providers, contributing to improved visitor experiences, increased customer loyalty, and more competitive and sustainable smart tourism ecosystems. This project is done in collaboration with Dr. Andreas Gregoriades from Cyprus University of Technology and Dr. Maria Pampaka from The University of Manchester, UK.
