Self-Deployment of Future Indoor Wi-Fi Networks: An Artificial Intelligence Approach

Atawia, Ramy; Gacanin, Haris

doi:10.1109/glocom.2017.8254611

Cited by 14 publications

(19 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent successful attempt to shift from the knowledgediscovery toward knowledge-driven (autonomous) operation has been made in [11], where an autonomous agent is presented to address the problem of self-deployment of non-stationary radio nodes. In [12], the authors present a wireless environment-specific RL agent with Q-learning to solve a selfoptimization problem with joint channel association and location optimization by retaining and reusing past experiences to reason out new optimization strategy.…”

Section: Related Workmentioning

confidence: 99%

“…By looking beyond recent data-driven paradigm with ML [6]- [10], this forward-looking paper elaborates the concept of machine intelligence in wireless systems. Machine intelligence employs broader disciplines of AI such as sensing, reasoning, active learning, and knowledge management [11], [12]. With AI intelligent systems can be designed to perform "autonomous" tasks (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Autonomous Wireless Systems With Artificial Intelligence: A Knowledge Management Perspective

Gacanin

2019

IEEE Veh. Technol. Mag.

Self Cite

View full text Add to dashboard Cite

This paper discusses technology and opportunities to embrace artificial intelligence (AI) in the design of autonomous wireless systems. We aim to provide readers with motivation and general AI methodology of autonomous agents in the context of self-organization in real time by unifying knowledge management with sensing, reasoning and active learning. We highlight differences between training-based methods for matching problems and training-free methods for environmentspecific problems. Finally, we conceptually introduce the functions of autonomous agent with knowledge management. Data-driven Self-organizing NetworkThese are the traditional SON functions [3]: 1) selfconfiguration (e.g. learning of configuration parameters, neighbors), 2) self-optimization (e.g. learning in mobility, load, handover, interference, capacity and coverage optimization) and 3) self-healing (e.g. fault analysis, detection). The

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Autonomous Wireless Systems With Artificial Intelligence: A Knowledge Management Perspective

Gacanin

2019

IEEE Veh. Technol. Mag.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The major challenge in this case is coupling customer demands and network resources in real time. This may be accomplished by utilization of supervised, unsupervised, and reinforcement learning with methods mentioned in Table 1 [3], [6], [9], [12].…”

Section: A Operator-related Challengesmentioning

confidence: 99%

“…non-linear and probabilistic reasoning methods) such as belief networks, Markov models, neural networks, reinforcement learning, etc. For example, network planning and deployment in ultra-dense scenarios would leverage AI to enrich the optimization process, while multi-agent learning and customer-guided decision making remain open questions in location-search for deployment of new access points (APs) [12]. Further examples include network utilization through autonomous resource allocation, real-time optimization based on customer demand, load prediction, coverage optimization, etc.…”

Section: B Network-related Challengesmentioning

confidence: 99%

Artificial Intelligence Paradigm for Customer Experience Management in Next-Generation Networks: Challenges and Perspectives

Gacanin

Wagner

2019

IEEE Network

Self Cite

View full text Add to dashboard Cite

With advancements of next-generation programmable networks a traditional rule-based decisionmaking may not be able to adapt effectively to changing network and customer requirements and provide optimal customer experience. Customer experience management (CEM) components and implementation challenges with respect to operator, network, and business requirements must be understood to meet required demands. This paper gives an overview of CEM components and their design challenges. We elaborate on data analytics and artificial intelligence driven CEM and their functional differences. This overview provides a path toward autonomous CEM framework in next-generation networks and sets the groundwork for future enhancements.

show abstract

“…on the signal propagation. Other works, such as [7], deal with the determination of the most appropriate locations of Wi-Fi extenders. On the other side, it is envisaged that the efficiency of automated network management processes can be substantially enhanced through the exploitation of powerful data analytics technologies able to process the large amount of data that can be collected from Wi-Fi networks by powerful monitoring systems.…”

Section: Introductionmentioning

confidence: 99%

A New Self-planning Methodology Based on Signal Quality and User Traffic in Wi-Fi Networks

Sánchez–González

Pérez‐Romero

Sallent

2019

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Wi-Fi networks have become one of the most popular technologies for the provisioning of multimedia services. Due to the exponential increase in the number of Access Points (AP) in these networks, the automation of the planning, configuration, optimization and management tasks has become of prime importance. The efficiency of these automated processes can be improved with the inclusion of data analytics mechanisms able to process the large amount of data that can be collected from Wi-Fi networks by powerful monitoring systems. This paper presents a new self-planning methodology that collects historical network measurements and extracts knowledge about user signal quality and traffic demands to determine adequate AP relocations. The performance of the proposed AP relocation methodology based on a genetic algorithm is validated in a real Wi-Fi network. The proposed approach can be easily adapted to other contexts such as small cell networks.

show abstract

Self-Deployment of Future Indoor Wi-Fi Networks: An Artificial Intelligence Approach

Cited by 14 publications

References 8 publications

Autonomous Wireless Systems With Artificial Intelligence: A Knowledge Management Perspective

Autonomous Wireless Systems With Artificial Intelligence: A Knowledge Management Perspective

Artificial Intelligence Paradigm for Customer Experience Management in Next-Generation Networks: Challenges and Perspectives

A New Self-planning Methodology Based on Signal Quality and User Traffic in Wi-Fi Networks

Contact Info

Product

Resources

About