Leveraging information-driven storage in an NFV Marketplace in the 5G ecosystem
KeywordsNetwork Function Virtualization ; Service Marketplace Platform ; Service Recommendation Engine ; Graph-based Recommender Sys- tems ; Item-item Collaborative Filtering ; 5G networks ; NoSQL databases ; Data mining
In the previous years, preliminary interest and discussions about a possible 5G standard have evolved into a full-fledged conversation that has captured the attention and imagination of researchers and engineers around the world. 5G networks expect to provide significant advances in network management compared to traditional mobile infrastructures by leveraging intelligence capabilities such as data analysis, prediction, pattern recognition and artificial intelligence. The telecommunications industry was one of the first to adopt data mining technology on the grounds that companies routinely generate and store enormous amounts of high-quality data, have a very large customer base, and operate in a rapidly changing and highly competitive environment. The ultimate goal of 5G era aims in automation and autonomy, where it’s an incomplete strategy to continue to focus only on identifying patterns. The digital transformation of network infrastructure through Network Function Virtualization (NFV) and Software Defined Networking (SDN) is anticipated to play a pivotal role with the respect to the commercialization of 5G. It is indubitable that the NFV comprises a key enabler in the composition of the 5G infrastructure. NFV provides the grounds for the efficient reformation of the existing mechanisms on the conformation of the networks and services, with Telecommunication Service Providers (TSPs) rapidly introducing new revenuegenerating services with a wider range of service requirements than ever before. Promptly, the exposure and the advertising of the available services across heterogeneous networks necessitates the establishment of a marketplace for their promotion and management of the relationships in different domains. In the network-centric business, the identification and discovery on the notion of decisions in modifying the the network are the real heart of the operation. Additionally, data-mining algorithms can offer substantial advantages based on virtualized components from a NFV marketplace, targeting at TSPs who request the commercialization of new virtualized products rapidly. The incorporation of an NFV Marketplace paves the way for expansion of the relationships between the TSPs and their own enterprise customers beyond just connectivity services. New business-to-business products can be offered to the enterprise customers, who can purchase them on demand. An NFV Marketplace bridges a plethora of gaps in the relationship of virtualized network infrastructure, cloud applications, orchestration, and commercialization tools through an ecosystem of partners as it enables the provisioning of new services, including third-party offerings and the personalization of bundles of services for different markets. On this concept, the increasing importance of the NFV Marketplace as a medium for electronic and business transactions has served as a driving force for the development of recommender systems, aiding the personalized service transactions. An important catalyst in this regard is the ease with which the NFV Marketplace enables users to provide feedback about preferences. In such cases, users are able to easily provide feedback and enhance the recommendation procedure. The subject of this MSc thesis is the introduction, the development and the integration of a novel NFV Marketplace, serving the entire storage, utilization and recommendation lifecycle of NFV artifacts in the 5G ecosystem. Going beyond a conventional data store, the NFV Marketplace delivers dynamic added-value mechanisms from the support of the developers in the provision of innovative storage and mining capabilities from the demand and supply sides respectively, addressing the needs of the diverse stakeholders. Additionally, the integration of innovative recommendation algorithms are incorporated in the NFV Marketplace with the aim of engaging personalized artifact recommendations to the customers, as to allow them to delve more deeply into the available business services without having to perform search after search.