Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org. © 2022 Copyright held by the owner/author(s). 0360-0300/2022/1-ART1 $15.00 http://dx.doi.org/10.1145/3524106 ACM Comput. Surv. A Survey on Requirements of Future Intelligent Networks: Solutions and Future Research Directions ARIF HUSEN, MUHAMMAD HASANAIN CHAUDARY, AND FAROOQ AHMAD Department of Computer Science at COMSATS University Islamabad, Lahore Campus, Pakistan The context of this study examines the requirements of Future Intelligent Networks (FIN), solutions, and current research directions through a survey technique. The background of this study is hinged on the applications of Machine Learning (ML) in the networking field. Through careful analysis of literature and real-world reports, we noted that ML has significantly expedited decision-making processes, enhanced intelligent automation, and helped resolve complex problems economically in different fields of life. Various researchers have also envisioned future networks incorporating intelligent functions and operations with the ML. Several efforts have been made to automate individual functions and operations in the networking domain; however, most of the existing ML models proposed in the literature lack several vital requirements. Hence, this study aims to present a comprehensive summary of the requirements of FIN and propose a taxonomy of different network functionalities that needs to be equipped with ML techniques. The core objectives of this study are to provide a taxonomy of requirements envisioned for end-to-end FIN, relevant ML techniques, and their analysis to find research gaps, open issues, and future research directions. The real benefit of machine learning applications in any domain can only be ensured if intelligent capabilities cover all its components. We obse rved that future generations of networks are heterogeneous, multi-vendor, and multidimensional, and ML can provide optimal results only if intelligent capabilities are used on a holistic scale. Realizing intelligence on a holistic scale is only possible if the ML algorithms can solve heterogeneous problems in a multi-vendor and multidimensional environment. ML models must be reliable and efficient, support distributed learning architecture, and possess the capability to learn and share the knowledge across the network layers and administrative domains to solve issues. Firstly, this study ascertains the requirements of the FIN and proposes their taxonomy through reviews on envisioned ideas by various researchers and articles gathered from reputed conferences and standard developing organizations using keyword queries. Secondly, we have reviewed existing studies on ML applications focusing on coverage, heterogeneity, distributed architecture, and cross-domain knowledge learning and sharing. Our study observed that in the past, ML applications were focused mainly on an individual/isolated level only, and aspects of global and deep holistic learning with cross-layer/domain knowledge sharing with agile ML operations are not explored at large. We recommend that the issues mentioned above be addressed with improved ML architecture and agile operations and propose ML pipeline-based architecture for FIN. The significant contribution of this study is the impetus for researchers to seek ML models suitable for a modular, distributed, multi-domain and multi-layer environment and provide decision-making on a global or holistic rather than individual function level. CCS Concepts: • Networks→Network design principles. Additional Key Words and Phrases: Future intelligent networks, global learning, cross-administrative domain learning, knowledge sharing, cross- layer learning, feature sharing, deep holistic learning. 1 Introduction Traditional networks are characterized by human-assisted daily operations along with rule-based automation and decision-making matters [1-3]. However, due to the continuous proliferation of AI applications in all fields of life, the networks must shift from the traditional approach to a new dimension [4]. The new approach requires networks to provide self-aware, customizable, flexible, and adaptable behavior with the assurance of security and privacy in its processes. These features are expected to be inducted into the 6G and beyond networks, formally referred to in this study as Future Intelligent Networks (FIN). The success of FIN relies on a dynamic service level isolation enabled by Network Slicing (NS) and intelligent decision-making capabilities provided by Machine Learning (ML) techniques for networks [5]. Several researchers have envisioned the usage scenarios of ML techniques for 6G networks to realize the intelligent capabilities in terms of autonomous operations and intelligent services. However, the intelligent capabilities will extend beyond the 6G vision due to continuous networking technologies and ML techniques developments. The 3rd Generation Partnership Project (3GPP) introduced the Network Slicing (NS) in Release-15 [6] to fulfill the service level isolation requirements with the help of several recent developments in networking and computing technologies. The isolation provided by these technologies can be physical or virtual depending upon the type of resources and functions used in a network [7]. Furthermore, the configuration and optimization of resources and functions can be performed with intelligent decision-making capabilities provided by the ML algorithms in an autonomous and adoptable way [8]. The need for intelligent behavior of networks is motivated by the crucial necessity to eliminate underlying infrastructure complexity and enable service-related information exchange between multiple networks and intelligent user devices in real-time [9-11]. Significant and beneficial future applications such as vehicular networks, autonomous vehicles, remote surgery, and the tactile internet will depend on the intelligent functionalities of networks. The aspects of smart services and networks have been discussed in the literature for the 6G and beyond era that will use ML capabilities intensively [12]. The intelligent capabilities to achieve self-aware automation will enhance performance in numerous essential aspects such as security, fault management, Quality of Service (QoS), Quality of Experience (QoE), and energy conservation. Furthermore, the edge devices that will be used in the future will have dedicated hardware capable of running localized ML algorithms in a distributed fashion that is of a different approach in comparison to the traditional concept of ML operations.