To align with sustainability goals, such as Net Zero Emissions, serverless providers must incorporate energy considerations into their resource management models. In edge computing environments, where resources are scarce and latency requirements are stringent, serverless frameworks like OpenFaaS and OpenWhisk commonly rely on Kubernetes for function allocation on edge nodes. However, these frameworks often overlook energy consumption as a critical decision factor, which leads to increased energy costs and higher operational expenses (OPEX). To address this gap, we introduce Go-Green-Go-Cheap (3GC) approach-a deadline-aware and cost-effective resource allocation strategy tailored for serverless service providers to minimize energy and execution costs. 3GC enables real-time resource allocation and leverages the per-core Dynamic Voltage and Frequency Scaling (DVFS) feature to finely tune the balance between execution time and energy consumption. Our evaluation demonstrates that 3GC surpasses existing allocation techniques, achieving cost savings of 39.35% up to 69.43%, while consistently meeting function latency requirements.

Intrusion Detection Systems (IDS) are critical for securing modern networks and systems; however, traditional IDS approaches often rely solely on network traffic or host-level data, limiting their ability to detect sophisticated threats such as AI-driven, zero-day, and polymorphic attacks. This limitation is even more pronounced in highly dynamic environments, such as cloud-based and containerized architectures, where the potential of leveraging rich contextual information remains underexplored. To address this gap, we propose a novel Multidimensional Intrusion Detection System (MIDS) approach that integrates multiple data dimensions, including network and container features, to enhance threat detection in containerized environments. By combining these dimensions, MIDS provides a holistic view of the cluster, enabling more comprehensive threat analysis and improved detection accuracy. We introduce a new data merging technique that unifies network flows with container metrics to facilitate multidimensional analysis. Due to the lack of existing datasets containing such heterogeneous data, we generated two MIDS datasets by simulating prevalent attacks on two well-known containerized applications deployed on Kubernetes (K8s): one using the Damn Vulnerable Web Application (DVWA) and the other using Google's Bank of Anthos (BoA). These simulations included Denial of Service (DoS), brute force, and SQL injection attacks. We evaluated state-of-the-art machine learning (ML) algorithms on these datasets, including SVM, XGBoost, and DNN. The experimental results demonstrate that using MIDS enables ML algorithms to achieve up to 8.69 % and 30.07 % higher F1 scores compared to using only network or container data, respectively. Feature analysis highlights the complementary contributions of network and container dimensions, showcasing the effectiveness of the proposed multidimensional approach for intrusion detection in containerized environments.

Facial images play a crucial role in many web and security applications, but their uses come with notable privacy risks. Despite the availability of various face anonymization algorithms, they often fail to withstand advanced attacks while struggling to maintain utility for subsequent applications. We present two novel face anonymization algorithms that utilize feature operations to overcome these limitations. The first algorithm utilizes perturbation and matching of high-level features, whereas the second algorithm enhances this approach by also incorporating perturbation of low-level features along with regularization. These algorithms significantly enhance the utility of anonymized images while ensuring differential privacy. Additionally, we introduce a task-based benchmark to enable fair and comprehensive evaluations of privacy and utility across different algorithms. Through experiments, we demonstrate that our algorithms outperform others in preserving the utility of anonymized facial images in classification tasks while effectively protecting against a wide range of attacks.

Abstract Virtual resource load prediction in network function virtualization (NFV) is the subject of intense research due to its crucial role in enabling proactive resource adaptation in dynamic NFV environments whose resource demand constantly changes. Several long short‐term memory (LSTM)‐based approaches have been proposed to forecast the resource load of multiple resource attributes of a virtual network function (VNF) in a service function chain (SFC). In this article, we present NFVLearn, a flexible multivariate, many‐to‐many LSTM‐based model which uses different types of resource load history (CPU, memory, I/O bandwidth) from various VNFs of an SFC to predict future loads of multiple resources of a VNF. We then compare four novel automated input selection frameworks for NFVLearn. Simulations on those frameworks based on graph neural networks, Pearson correlation coefficient, Spearman rank correlation coefficient, and Kendall rank correlation coefficient demonstrate that models using lesser, highly correlated input features retain high prediction root mean squared error accuracy and coefficients of determination scores by leveraging resource attribute inter‐dependencies from the SFC. Those results show that resource attribute interdependency‐based input feature selection frameworks can reduce overhead in the control plane while keeping high accuracy and high fidelity resource load prediction of multiple resource attributes.

Orchestration mechanisms play a pivotal role in assisting service providers in deploying their increasingly complex virtual network services seamlessly thanks to Network Function Virtualization (NFV) and Software-defined networking (SDN) technology enablers. Unfortunately, existing state-of-the-art orchestration techniques suffer from non-scalability and time-efficiency aptitude when the services require VNFs to be distributed across cloud and edge environments with complex dimensions. Furthermore, they provide competitive solutions in good execution time only for small-scale scenarios (e.g., in seconds for 50 nodes) but generally require an exorbitant amount of time to converge towards feasible solutions for medium-scale or even large-scale schemes. This paper proposes VAPNIC: an innovative approach that solves the VNF placement and chaining problem with lower algorithmic complexity using a disjoint-set data structure aided divide-and-conquer strategy. Our method's unique design is the non-use of any existing shortest path search algorithms to chain the virtual network functions. To the best of our knowledge, this is the first work that strives to tackle the placement and chaining of the VNFs from a distinctive perspective in the case of medium-and-large scale scenarios with a fast and scalable heuristic that exploits the divide-and-conquer design paradigm based on multi-branched recursion. Experimental results indicate that VAPNIC outperforms existing approaches in acceptance rate, resource utilization, scalability, and time efficiency.

Time-efficient and scalable mechanisms have a significant role in aiding cloud providers to deploy their increasingly complex virtual network services in a seamless manner thanks to Network Function Virtualization (NFV) and Software Defined Networking (SDN) paradigms. Unfortunately, existing state-of-the-art techniques suffer from non-scalability aptitude and often do not converge rapidly towards feasible solutions, although they provide competetive solutions in acceptable execution time for small-scale scenarios.In this paper, we propose RAFALE, a novel approach that formulates the orchestration problem as a graph matching problem and solves it using two exact algorithms. To the best of our knowledge, this is the first work that attempts to tackle the placement and chaining of the VNFs from a different perspective. Experimental results indicate that RAFALE outperforms, in terms of scalability and time-complexity, the well-known VF2 graph matching algorithm and two existing heuristic-based approaches for the placement and chaining of the VNFs.

One of the main challenges faced by cloud providers is the uncertainty in their workload, resulting from the high variability and the dynamic nature of clients' demands. The inability to meet those demands during peak times can lead to high service rejection rates, experienced delays, and consequently profit and reputation losses. The concept of cloud federation has been proposed as a way to address this challenge, by enabling a group of cloud providers to collaborate by dynamically combining their resources as needed, to satisfy received requests. Existing cloud federation approaches fail to consider clients' SLA requirements during the coalition formation process or provide a self-healing mechanism to deal with unexpected resources' shortage during operation. Furthermore, the state of the art approaches suffer from performance issues, such as high execution times, unstable performance, and lack of convergence to a solution in complex scenarios (e.g., requests with mixed, independent types of VMs). This paper proposes a novel social gaming based approach for coalition formation in the cloud that finds the best coalition of cloud providers to answer requests, while satisfying the clients' SLA requirements. The proposed algorithm, dubbed SLA Aware Cloud Coalition Formation algorithm (S-ACCF), leverages Irving's roommate algorithm to form a stable coalition of cloud providers, with a rapid execution time. The S-ACCF algorithm is designed to maximize the coalition's profit, while minimizing the number of participants in the coalition as well as the penalty incurred by providers who fail to offer all or some of the promised resources using a self-healing process. The S-ACCF algorithm was extensively tested using a variety of scenarios, and its performance was compared to two state of the art approaches: 1) the Optimal Cloud Federation Mechanism (OCFM) that relies on an exhaustive search of all possible solutions to find the best coalition; and 2) the Cloud Federation Formation Mechanism (CFFM) that relies on an iterative split-and-merge approach to find the best coalition. While the optimal approach (OCFM) always finds the best coalition leading to the highest collective profit, it has an exponential time complexity, thus leading to very large execution times. On the other hand, the split-and-merge approach (CFFM), which relies on random selection of sub-groups for coalition formation, suffers from instability (different results in repeated runs), high and variable execution time, and a noticeable requests' rejection rate that changes between runs. The test results show that the S-ACCF algorithm addresses the limitations of the OCFM and the CFFM algorithms, and outperforms the optimal and split-and-merge approaches in terms of execution time, individual provider payoff, and the number of providers per coalition. Furthermore, it yields higher stability and zero rejection rate, when compared to the split-and-merge approach. Indeed, our proposed approach yields an execution time that is 12 to 25 times faster than the optimal and split-and-merge approaches, which is a major advantage for real-time applications. Moreover, when compared to the two other approaches, our S-ACCF algorithm always finds the smallest coalition possible satisfying the client requirements, thus leading to the highest individual payoff for providers and lower administration overhead. Finally, unlike the split-and-merge approach, our algorithm shows a stable performance, and converges towards the optimal solution in simple and complex scenarios, thus making it suitable for production environments.

Multi-persona mobile computing has begun to make its way to determine the battle about practical strategy for adopting personal devices in workplace. Though its competency, multi-persona performance and viability are critically threatened by the limited resources of mobile devices. In recent years, mobile edge computing (MEC) has risen as promising paradigm within the internet of things era bringing benefits to the proximity of mobile terminals, leveraging intelligent computations offloading services to address the severity of their resource scarcity. Yet, embracing mobile edge-based services to augment personas resources and performance raises new concerns including determining what computations to offload for serving the highest number of mobile devices and reducing the remote execution fees imposed on the institution. In this context, we propose new cost-effective MEC-based solution to address these issues. We develop two-level multi-objective optimization realized through an intelligent offloading decision model able to settle both concerns, by minimizing processing, memory and energy while augmenting virtual mobile instances performance on a wide range of physical devices with minimal offloading service fees. We also propose a redesigned smart genetic-based method able to accelerate and reduce the overhead of offloading decision evaluation. Extensive analysis is performed and the results show that our proposition can get more quickly the offloading strategy than other schemes. The results also demonstrate the ability to enforce the virtual mobile devices by reducing local processing, memory usage, energy consumption and execution time along with acceptable minimal additional fees compared to other techniques.

Cloud computing has long been the main backbone that Internet of Things (IoT) devices rely on to accommodate their storage and analytical needs. However, the fact that cloud systems are often located quite far from the IoT devices and the emergence of delay-critical IoT applications urged the need for extending the cloud architecture to support delay-critical services. Given that fog nodes possess low resource capabilities compared to the cloud, matching the IoT services to appropriate fog nodes while guaranteeing minimal delay for IoT services and efficient resource utilization on fog nodes becomes quite challenging. In this context, the main limitation of existing approaches is addressing the scheduling problem from one side perspective, i.e., either fog nodes or IoT devices. To address this problem, we propose in this paper a multi-criteria intelligent IoT-Fog scheduling approach using game theory. Our solution consists of designing (1) preference functions for the IoT and fog layers to enable them to rank each other based on several criteria latency and resource utilization and (2) centralized and distributed intelligent scheduling algorithms that capitalize on matching theory and consider the preferences of both parties. Simulation results reveal that our solution outperforms the two common Min-Min and Max-Min scheduling approaches in terms of IoT services execution makespan and fog nodes resource consolidation efficiency.

The energy consumption growth of the Information and Communication Technology (ICT) sector contributes to almost 2% of the global carbon footprint with an estimated trend of 3-3.6% by 2020. Most of this growth (45%) can be attributed to data centers (DC) which now represent the core infrastructure for different industries. Furthermore, cloud DCs are complex systems composed of several ICT and non-ICT (i.e. mechanical and electrical) sub-systems. The variety of configurations and the inter-dependencies of the different DC sub-systems leads to enormous challenges in understanding and optimizing DC energy efficiency based on the Power Usage Effectiveness (PUE) metric. Within this context, we focus in this work on analyzing the behavior of Deep Neural Network (DNN)-based model to predict the DC energy efficiency metric (PUE). In fact, the proposed model is used to evaluate the impact of various DC sub-systems on energy efficiency. Through an experimentation with real datasets from a real DC, we observed that DNN-based model achieves a good Root Mean Square Error (RMSE). The obtained results of this experimentation indicate that our proposed DNN-based model improves the PUE optimization, and consequently, shows its promise for a practical implementation.

The IP Multimedia System (IMS) is an important reference service delivery platform for next generation networks and is considered as a de-facto standard for IP-based multimedia communication services. In its current design, the IMS faces important challenges in terms of scalability and elasticity, and lacks the ability to adaptively manage the network resources and dynamically dimension the network nodes based on load and demand. While Virtualized IMS deployments can partially address those limitations, IMS cloud providers still need to address challenges related to the high variability and uncertainty in their workloads, which could lead to poor QoS, high delays, and reputation and financial losses. The concept of cloud federation has been recently proposed to address such challenges. This concept enables a group of cloud providers to collaborate and form a cloud coalition that dynamically combines the participants' resources as needed, to meet variable users' demands. In this work, we propose a novel and customized IMS clouds' federation approach, that is inspired by the game theoretic roommate matching algorithm. The proposed algorithm aims at maximizing the coalition profit while minimizing the penalties incurred by violated SLAs. Our proposed solution was implemented and compared to the optimal and split-and-merge cloud federation formation approaches. The simulation results obtained show that our approach outperforms the optimal and the split-and-merge approaches in terms of execution time, while always yielding the same solution as the optimal approach in the cases tested, thus making it a strong contender for practical deployments.

Fueled by changes in professional application models, personal interests and desires and technological advances in mobile devices, multi-persona has emerged recently to keep balance between different aspects, in our daily life, on a single mobile terminal. In this context, mobile virtualization technology has turned the corner and currently heading towards widespread adoption to realize multi-persona. Although recent lightweight virtualization techniques were able to maintain balance between security and scalability of personas, the limited CPU power and insufficient memory and battery capacities, still threaten personas performance and viability. Throughout the last few years, cloud computing has cultivated and refined the concept of outsourcing computing resources, and nowadays, in the coming age of smartphones and tablets, the prerequisites are met for importing cloud computing to support resource constrained mobiles. From these premises, we propose in this paper a novel offloading-based approach that based on global resource usage monitoring, generic and adaptable problem formulation and heuristic decision making, is capable of augmenting personas performance and viability on mobile terminals. The experiments show its capability of reducing the resource usage overhead and energy consumption of the applications running in each persona, accelerating their execution and improving their scalability, allowing better adoption of multi-persona solution.

Personalization of serious games is an important factor for motivating and engaging players. It requires the identification of players' profiles through the analysis of large volume of data including game data. This research study aims at identifying relevant data from an online serious game and the appropriate data mining methods for deduction of players' profiles. Multiple linear regression is applied to analyze the influence of player's characteristics on his performance. Moreover, clustering technique is used, in particular K-means, to extract players' clusters and to identify their common characteristics. The regression models showed that the number of access to the game, completed quests and advantages used contribute significantly to the scores and the gaming duration, while the clustering revealed three forms of players' participation: beginner, intermediate and advanced; who interact with the game according to their experiences.

Mobile virtualization is a key technology that is witnessing widespread adoption to realize multi-persona functionality capable of accommodating work, personal, and mobility needs on a single mobile terminal. Yet, unlike virtualization on servers and desktop machines, mobile virtualization is more challenging due to the limited resources on mobiles platforms in terms of CPU, memory and battery. The evolution of mobile virtualization ranged from heavy to more lightweight techniques capable of running virtual environments on mobile devices with lower overhead. Even though the latest proposed lightweight approaches were able to realize multi-persona, yet none of them is capable of efficiently managing personas performance or ensuring their viability. In parallel, to address the resource limitations of mobile platforms, many researchers have proposed offloading techniques to migrate computation intensive components out of the mobile device to be executed on resourceful mobile cloud computing infrastructure. Motivated by their promising results, we propose in this paper the integration of offloading in the virtual environments on the mobile device toward augmenting personas performance and ensuring their viability. Our experiments show very promising results in this regard.

Network virtualization is considered as a promising way to overcome the limitations and fight the gradual ossification of the current Internet infrastructure. The network virtualization concept consists in the dynamic creation of several co-existing logical network instances (or virtual networks) over a shared physical network infrastructure. One of the challenges associated with this concept is the dynamic discovery and selection of virtual resources that can be composed to form virtual networks. To achieve that task, there is a need for a formal and expressive information model facilitating information representation and sharing between the various roles/entities involved. We have previously proposed a service-oriented hierarchical business model for virtual networking environments, as well as an architecture enabling its realization. In this paper, we build on this business model and architecture by proposing a multiservice, multi-role hierarchical information model, for virtual networking environments. Furthermore, we demonstrate the usage of this information model using a secure content distribution scenario that is realized using REST interfaces. Unlike other proposals, our integrated information model enables the fine-grained description of virtual networks and virtual networking resources, in addition to the modeling of network services and roles, and their relationships and hierarchy.

Network virtualization is a promising and technically challenging concept, which enables the dynamic creation of several co-existing logical network instances (or virtual networks) over a shared physical network infrastructure. There are several motivations behind this concept, including: cost-effective sharing of resources; customizable networking solutions; and the convergence of existing network infrastructures. We have previously proposed a new business model for virtual networking environments. In this paper, we use this model as well as concrete use cases as basis for the definition of the Open Virtual Playground - an open virtual multi-services networking architecture in which different levels of services (i.e. essential services, service enablers, service building blocks, and end-user services) offered by various players, can be dynamically discovered, used, and composed. Furthermore, a QoS-enabled VoIP service scenario is used to demonstrate the system operation and preliminary performance measurements are collected.

In wireless networks, efficient management of mobility is a crucial issue to support mobile users. The mobile Internet protocol (MIP) has been proposed to support global mobility in IP networks. Several mobility management strategies have been proposed which aim reducing the signaling traffic related to the Mobile Terminals (MTs) registration with the Home Agents (HAs) whenever their Care-of-Addresses (CoAs) change. They use different foreign agents (FAs) and Gateway FAs (GFAs) hierarchies to concentrate the registration processes. For high-mobility MTs, the Hierarchical MIP (HMIP) and Dynamic HMIP (DHMIP) strategies localize the registration in FAs and GFAs, yielding to high-mobility signaling. The Multicast HMIP strategy limits the registration processes in the GFAs. For high-mobility MTs, it provides lowest mobility signaling delay compared to the HMIP and DHMIP approaches. However, it is resource consuming strategy unless for frequent MT mobility. Hence, we propose an analytic model to evaluate the mean signaling delay and the mean bandwidth per call according to the type of MT mobility. In our analysis, the MHMIP outperforms the DHMIP and MIP strategies in almost all the studied cases. The main contribution of this paper is the analytic model that allows the mobility management approaches performance evaluation.

Third generation (3G) technologies are becoming more widely deployed. However, a prerequisite for the successful deployment of such services is the measurement of practical performance characteristics offered by the underlying wireless network (e.g. 3G). This paper presents the results of a number of experiments aiming to identify the performance of a real WCDMA (wideband code division multiple access) -based wireless network for different types of applications: FTP, HTTP, VoIP, and audio and video streaming. Moreover, the paper discusses the impact on the measured performance by assigning different QoS profiles to end-users. Based on the evaluation results, the paper provides a set of recommendations for both operators and service developers when designing and deploying applications on such wireless networks. These recommendations can also help researchers in accurately validating 3G wireless network research proposals.