5G networks are expected to support various services and applications with more stringent latency, reliability, and bandwidth requirements than previous generations. Open Radio Access Networks (O-RAN) have been proposed to meet these requirements. The O-RAN Alliance assumes O-RAN components to be Virtualized Network Functions (VNFs). Furthermore, O-RAN allows employing Machine Learning (ML) solutions to tackle challenges in resource management. However, intelligently managing resources for O-RAN can be proved challenging. Network providers need to scale resources in response to incoming traffic dynamically. Elastically allocating resources provides higher flexibility, reduces OPerational EXpenditure (OPEX), and increases resource utilization. In this work, we propose and evaluate an elastic VNF orchestration framework for O-RAN. The proposed system consists of a traffic forecasting-based dynamic scaling scheme using ML and a Reinforcement Learning (RL) based VNF placement policy. The models are evaluated based on their predictive capabilities subject to all Service-Level Agreements.

Due to the huge surge in the traffic of IoT devices and applications, mobile networks require a new paradigm shift to handle such demand roll out. With the 5G economics, those networks should provide virtualized multi-vendor and intelligent systems that can scale and efficiently optimize the investment of the underlying infrastructure. Therefore, the market stakeholders have proposed the Open Radio Access Network (O-RAN) as one of the solutions to improve the network performance, agility, and time-to-market of new applications. O-RAN harnesses the power of artificial intelligence, cloud computing, and new network technologies (NFV and SDN) to allow operators to manage their infrastructure in a cost-efficient manner. Therefore, it is necessary to address the O-RAN performance and availability challenges autonomously while maintaining the quality of service. In this work, we propose an optimized deployment strategy for the virtualized O-RAN units in the O-Cloud to minimize the network's outage while complying with the performance and operational requirements. The model's evaluation provides an optimal deployment strategy that maximizes the network's overall availability and adheres to the O-RAN-specific requirements.

Different challenges are facing the adoption of cloud-based applications, including high availability (HA), energy, and other performance demands. Therefore, an integrated solution that addresses these issues is critical for cloud services. Cloud providers promise the HA of their infrastructure while cloud tenants are encouraged to deploy their applications across multiple availability zones. Moreover, the environmental and cost impacts of running applications in the cloud are integral parts of incorporated responsibility where the cloud providers and tenants intend to reduce. Hence, an analytical stochastic model is needed for the tenants and providers to quantify the expected availability offered by an application deployment. If multiple deployment options can satisfy the HA requirement, the question remains, how can we choose the deployment that satisfies the other providers and tenants requirements? Therefore, this paper proposes a cloud scoring system and integrates it with a Stochastic Petri Net model. While the Petri Net model evaluates the availability of cloud applications deployments, the scoring system selects the optimal HA-aware deployment in terms of energy, operational expenditure, and other norms. We illustrate our approach with a use case that shows how we can use the various deployment options to satisfy both the cloud tenant and provider needs.

The shift towards a completely virtualized networking environment is triggered by the emergence of software defined networking and network function virtualization (NFV). Network service providers have unlocked immense capabilities by these technologies, which have enabled them to dynamically adapt to user needs by deploying their network services in real-time through generating Service Function Chain (SFCs). However, NFV still faces challenges that hinder its full potentials, including availability guarantees, network security, and other performance requirements. For this reason, the deployment of NFV applications remains critical as it should meet different service level agreements while insuring the security of the virtualized functions. In this paper, we tackle the challenge of securing these SFCs by introducing virtual security functions (VSFs) into the latency-aware deployment of NFV applications. This work insures the optimal placement of the SFC components including the security functions while considering the performance constraints and the VSFs' operational rules such as, functions' alliance, proximity, and anti-affinity. This paper develops a mixed integer linear programming model to optimally place all the requested SFCs while satisfying the above constraints and minimizing the latency of every SFC and the intercommunication delay between the SFC components. The simulations are evaluated against a greedy algorithm on the virtualized Evolved Packet Core use case and have shown promising results in maintaining the security rules while achieving minimum delays.

With the growing demand for data connectivity, network service providers are faced with the task of reducing their capital and operational expenses while simultaneously improving network performance and addressing the increased connectivity demand. Although Network Function Virtualization (NFV) has been identified as a solution, several challenges must be addressed to ensure its feasibility. In this paper, we address the Virtual Network Function (VNF) placement problem by developing a machine learning decision tree model that learns from the effective placement of the various VNF instances forming a Service Function Chain (SFC). The model takes several performance-related features from the network as an input and selects the placement of the various VNF instances on network servers with the objective of minimizing the delay between dependent VNF instances. The benefits of using machine learning are realized by moving away from a complex mathematical modelling of the system and towards a data-based understanding of the system. Using the Evolved Packet Core (EPC) as a use case, we evaluate our model on different data center networks and compare it to the BACON algorithm in terms of the delay between interconnected components and the total delay across the SFC. Furthermore, a time complexity analysis is performed to show the effectiveness of the model in NFV applications.

Network function virtualization (NFV) has been introduced by network service providers to overcome various challenges that hinder them from satisfying the growing demand for networking services with higher return-on-investment. The association of NFV with the leading technologies of information technology virtualization and software defined networking is paving the way for flexible and dynamic orchestration of the VNFs, but still, various challenges need to be addressed. The VNFs instantiation and placement problems on data center's (DC) servers are key enablers to achieve the desired flexible and dynamic NFV applications. In this paper, we have addressed the VNF placement problem by providing a novel mixed integer linear programming (MILP) optimization model and a novel heuristic solution, Betweenness centrality Algorithm for Component Orchestration of NFV platform (BACON), for small- and large-scale DC networks. The proposed solution addresses the VNF placement while taking into consideration the carrier-grade nature of the NFV applications and at the same time, minimizing the intra- and end-to-end delays of the service function chain (SFC). Also, the proposed approach enhances the reliability and the quality of service (QoS) of the SFC by maximizing the count of the functional group members. To evaluate the performance of the proposed solution, this paper conducts a comparative analysis with an NFV-agnostic algorithm and a greedy-k-NFV approach, which is proposed in the literature work. Also, this paper defines the complexity and the order of magnitude of the MILP model and BACON. BACON outperforms the greedy algorithms especially the greedy-k-NFV solution and has a lower complexity, which is calculated as O((n3-n2)/2). The simulation results show that finding an optimized VNF placement can achieve minimal SFCs delays and enhance the QoS accordingly.

Summary Cloud computing and its service models, such as Platform as a Service (PaaS), have changed the way that computing resources are allocated to Information and Communications Technology enterprises and users. Although multiple cloud providers support dynamic service provisioning, it is necessary to facilitate the management of the cloud infrastructure and applications in order to allow the continuous refinement of cloud models. Therefore, issues are raised regarding the cloud orchestration, including the flexible portability and interoperability of cloud applications among multiple cloud providers. Having said that, there is a need for a standardized design and management of the cloud use cases (during the creation of scenarios, application's deployment, and patching) to ensure efficient applications' migration between different providers. This paper proposes an artifact, GITS, a generic input template for CloudSim and other cloud simulators. GITS can be provided by PaaS offering to manage the creation, monitoring, administration, and patching of infrastructure and applications in the cloud. GITS defines the cloud schema that can be used with conforming cloud models and independent cloud providers; thus, portability and interoperability can be enabled in PaaS cloud models. GITS focuses on the architecture‐based modeling for cloud infrastructure and application not only in terms of computational resources but also in terms of high availability properties associated with infrastructure and applications. The main objective of the GITS template is to provide the cloud user with a modular, simple, readable, and reusable model that still supports the essential components and provide them with the ability to control the applications' execution, deployment, and other management needs in addition to the allocation environment. This paper describes GITS usage, specifically as an input template for CloudSim.

In the interconnected globe where service delivery is the success measure, cloud high availability (HA) is an indispensable area for enterprises. An HA-aware cloud system provides different approaches to handle the outages. This includes geo-redundancy, failover schemes, and HA-aware placement solutions. However, using real-cloud platforms to model HA-aware approaches is hindered by the configuration settings. To this end, simulation tools, such as CloudSim, can be used to evaluate HA solutions and a cloud resiliency against failures. CloudSim allows implementing of scheduling policies, but it does not support HA properties. This paper provides availability-aware CloudSim extension (ACE). ACE extends CloudSim with a graphical and textual modeling to ensure simplicity and reusability of cloud scenarios. ACE has added HA-aware modeling (HA metrics and failure/redundancy/interdependency models) and HA-aware scheduling (HA-aware placements, failover, repair, and load balancing policies) into CloudSim. With ACE, the creation of cloud scenarios is facilitated, and multiple HA-aware deployment solutions can be evaluated under different stochastic and deterministic events. ACE can assess the impact of different redundancy/failure models, and other performance policies to extract HA-aware lessons. In this paper, ACE is assessed on a cloud application to evaluate different redundancy/failure models and provide availability analysis of the HA-aware placement solution.

The growing dependency of users on social media, telecommunication services, mobile applications, banking amenities, and other cloud services requires a plan that mitigates inevitable failures and ensures the always-on access to these services. This emanates high availability (HA) concerns regarding the adoption of cloud. To maintain HA, the cloud provider and/or user should design a system that is immune to both application and infrastructure failures. This paper proposes live migration approach to maintain service delivery upon a sudden failure, a virtual machine (VM)/infrastructure overload, or maintenance. It develops a mixed integer linear programming model that minimizes the migration downtime based on the VM memory pages and the optimal HA-aware placement of the VM. It also provides different design considerations to achieve HA-aware applications placement. The proposed placement is used in the migration approach to find new hosts for the VMs. It considers VMs/applications deployments in geographically distributed data centers and satisfies redundancy, applications interdependency, and other HA and performance requirements. Then the deployments are assessed using a formal Petri Net model to improve them in terms of HA. The HA-aware placement and migration approaches are evaluated on 3-tier Web applications.

High availability (HA) is a main key performance indicator for cloud deployed services. Cloud providers offer different availability zones possibly located in different geographical regions. To protect cloud services against failures and natural disasters, it is recommended to deploy the applications on redundant resources across multiple zones and distribute the workload through a load-balancer. Different cloud infrastructure, located in different geographical zones with different energy source powering, hardware quality, etc., may have different reliability levels. Scheduling a cloud service on different zones while meeting the service level agreement availability requirements necessitate a solution to assess the expected availability of a given deployment. To quantify the expected availability offered by an application deployment, a formal stochastic model is required to capture the stochastic behavior of failures. This paper proposes a stochastic Petri Net model that captures the stochastic characteristics of cloud services and translates them into elements of an availability model. The model evaluates the availability of cloud services and their deployments in geographically distributed data centers (DCs). The results are useful to generate guidelines for an HA-aware scheduling.

Cloud computing promises flexible integration of the compute capabilities for on-demand access through the concept of virtualization. However, uncertainties are raised regarding the high availability of the cloud-hosted applications. High availability is a crucial requirement for multi-tier applications providing business services for a broad range of enterprises. This paper proposes a novel component high availability-aware scheduling technique, CHASE, which maximizes the availability of applications without violating service level agreements with the end-users. Using CHASE, prior criticality analysis is conducted on applications to schedule them based on their impact on their execution environment and business functionality. This paper presents the advantages and shortcomings of CHASE compared to an optimal solution, Open Stack Nova scheduler, high availability-agnostic, and redundancy-agnostic schedulers. The evaluation results demonstrate that the proposed solution improves the availability of the scheduled components compared to the latter schedulers. CHASE prototype is also defined for runtime scheduling in Open Stack environment.

Cloud computing is continuously growing as a business model for hosting information and communication technology applications. Although on-demand resource consumption and faster deployment time make this model appealing for the enterprise, other concerns arise regarding the quality of service offered by the cloud. One major concern is the high availability of applications hosted in the cloud. This paper demonstrates the tremendous effect that the placement strategy for virtual machines hosting applications has on the high availability of the services provided by these applications. In addition, a novel scheduling technique is presented that takes into consideration the interdependencies between applications components and other constraints such as communication delay tolerance and resource utilization. The problem is formulated as a linear programming multi-constraint optimization model. The evaluation results demonstrate that the proposed solution improves the availability of the scheduled components compared to OpenStack Nova scheduler.