Semi-Adaptive Evolution with Spontaneous Modularity of Half-Chaotic Randomly Growing Autonomous and Open Networks

Up until now, studies of Kauffman network stability have focused on the conditions resulting from the structure of the network. Negative feedbacks have been modeled as ice (nodes that do not change their state) in an ordered phase but this blocks the possibility of breaking out of the range of correct operation. This first, very simplified approximation leads to some incorrect conclusions, e.g., that life is on the edge of chaos. We develop a second approximation, which discovers half-chaos and shows its properties. In previous works, half-chaos has been confirmed in autonomous networks, but only using node function disturbance, which does not change the network structure. Now we examine half-chaos during network growth by adding and removing nodes as a disturbance in autonomous and open networks. In such evolutions controlled by a ‘small change’ of functioning after disturbance, the half-chaos is kept but spontaneous modularity emerges and blurs the picture. Half-chaos is a state to be expected in most of the real systems studied, therefore the determinants of the variability that maintains the half-chaos are particularly important in the application of complex network knowledge.

Intent-Driven Network and Service Management: Definitions, Modeling and Implementation

<div>Cognitive Autonomous Networks require the network to be able to derive and execute intelligent decisions, and thereby elevating the human operator's role to a higher level of abstraction where the operator can only specify the desired outcomes from the network. These abstract inputs, called intents, must be supported by corresponding intent-driven capabilities in the network or its management functions.</div><div>Although, Intent-Driven Management (IDM) has been published in multiple works, there is still no globally agreed end-to-end view of such IDM systems, let alone a globally agreed definition of intents. This paper provides a comprehensive discussion on the core aspects of IDM systems and combines them into an end-to-end system view with the related example solutions. Contrasting against a short review of related scientific and standards literature, the paper introduces a flexible, generic definition of intents and an End-to-End IDM System Architecture as well as the related modeling of intents to support their standardization. The paper also introduces implementation examples fitting the architecture and discusses advanced IDM features that need to be provided, including the ability to detect and resolve conflicts among intents.</div>

Intent-Driven Network and Service Management: Definitions, Modeling and Implementation

<div>Cognitive Autonomous Networks require the network to be able to derive and execute intelligent decisions, and thereby elevating the human operator's role to a higher level of abstraction where the operator can only specify the desired outcomes from the network. These abstract inputs, called intents, must be supported by corresponding intent-driven capabilities in the network or its management functions.</div><div>Although, Intent-Driven Management (IDM) has been published in multiple works, there is still no globally agreed end-to-end view of such IDM systems, let alone a globally agreed definition of intents. This paper provides a comprehensive discussion on the core aspects of IDM systems and combines them into an end-to-end system view with the related example solutions. Contrasting against a short review of related scientific and standards literature, the paper introduces a flexible, generic definition of intents and an End-to-End IDM System Architecture as well as the related modeling of intents to support their standardization. The paper also introduces implementation examples fitting the architecture and discusses advanced IDM features that need to be provided, including the ability to detect and resolve conflicts among intents.</div>

I2BN: Intelligent Intent Based Networks

Intent based network management reduces the complexity of network programming from a growing set of deeply technical APIs to context-free high-level objectives that the network should autonomously achieve and keep. The practical implementation of an intent based network requires substantial automation technology embedded in the network. Automation should cover the entire lifecycle of intents, from their ingestion to fulfillment and assurance. This article investigates the feasibility of automatically assembling interworking implementation units into intent specific automation pipelines, where units are reusable self-learning closed loop micro-services with self-declared capabilities. Each closed loop may gain knowledge and respond to dynamically changing network conditions, thereby enabling network autonomy in reaching the declared intent objectives. The human-network intent interface for expressing intents is proposed to be based on the aggregation of the deployed network and service automation capabilities, rather than a formalism decoupled from the actual network implementation. This principle removes the ambiguity and compatibility gap between human intent definition and machine intent fulfillment, while retaining the flexibility and extendibility of the intents offered by any specific system via onboarding additional micro-services with novel capabilities. The concepts discussed by the article fit into the architecture and closed loop work items already defined by ETSI ZSM and provides considerations towards new areas such as intent driven autonomous networks and enablers for automation.

Evolutionary Autonomous Networks

The communication networks of today can greatly benefit from autonomous operation and adaptation, not only due to the implicit cost savings, but also because autonomy will enable functionalities that are infeasible today. Across industry, academia and standardisation bodies there has been an increased interest in achieving the autonomous goal, but a path on how to attain this goal is still unclear. In this paper we present our vision for the future of autonomous networking. We introduce the concepts and technological means to achieve autonomy and propose an architecture which emerges directly through the application of these concepts, highlighting opportunities and challenges for standardisation. We argue that only a holistic architecture based on hierarchies of hybrid learning, functional composition, and online experimental evaluation is expressive and capable enough to realise true autonomy within communication networks.