5Growth Data-Driven AI-Based Scaling

Vleeschauwer, Danny De; Baranda, Jorge; Mangues‐Bafalluy, Josep; Chiasserini, Carla Fabiana; Malinverno, Marco; Puligheddu, Corrado; Magoula, Lina; Martín‐Pérez, Jorge; Barmpounakis, Sokratis; Kondepu, Koteswararao; Valcarenzhi, Luca; Li, Xi; Papagianni, Chrysa; García‐Saavedra, Andrés

doi:10.1109/eucnc/6gsummit51104.2021.9482476

Cited by 3 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of IoT and machine learning-based approaches has been highlighted as a future direction in urban solid waste management, particularly in addressing climate-induced risks in developing countries (Rakib et al, 2021). Additionally, the potential of 5G-driven AI-based scaling has been integrated into service management software platforms, indicating the importance of advanced technologies in waste management (Vleeschauwer et al, 2021). Sustainable and inclusive approaches for the future of waste management have been emphasized in various studies.…”

Section: Future Directionsmentioning

confidence: 99%

Ai-Driven Waste Management Systems: A Comparative Review of Innovations in the Usa and Africa

Zamathula Queen Sikhakhane Nwokediegwu,

Ejike David Ugwuanyi,

Michael Ayorinde Dada

et al. 2024

Eng. sci. technol. j.

View full text Add to dashboard Cite

The burgeoning challenges of waste management have propelled the integration of artificial intelligence (AI) into waste management systems, aiming to enhance efficiency, sustainability, and environmental impact. This abstract delves into the comparative review of AI-driven waste management innovations in the USA and Africa, illuminating the divergent strategies employed to address distinct contextual demands. In the USA, where waste management infrastructures are relatively advanced, AI technologies are leveraged to optimize waste collection routes, automate sorting processes, and enhance recycling efficiency. Machine learning algorithms analyze historical data to predict waste generation patterns, enabling municipalities to allocate resources more effectively. Additionally, robotic sorting systems equipped with computer vision contribute to the accurate segregation of recyclables, reducing contamination and promoting a circular economy. Conversely, in Africa, where waste management infrastructures may be less developed, AI applications prioritize scalable and adaptable solutions. Mobile applications powered by AI facilitate crowd-sourced waste reporting, enabling citizens to actively participate in waste management efforts. Furthermore, sensor-equipped smart bins optimize collection routes in real-time, improving resource utilization. The emphasis on community engagement and decentralized solutions reflects the unique challenges and opportunities present in African waste management contexts. Despite these regional disparities, common themes emerge, such as the role of data analytics, automation, and community involvement in shaping effective waste management systems. The comparative analysis underscores the importance of tailoring AI-driven innovations to the specific socio-economic and infrastructural landscapes of each region. Ultimately, understanding the nuanced approaches in the USA and Africa can inform a more holistic and globally adaptable framework for AI-driven waste management systems. Keywords: Al, Waste Management, USA, Africa, Innovation, Sanitation.

show abstract

Section: Future Directionsmentioning

confidence: 99%

Ai-Driven Waste Management Systems: A Comparative Review of Innovations in the Usa and Africa

Zamathula Queen Sikhakhane Nwokediegwu,

Ejike David Ugwuanyi,

Michael Ayorinde Dada

et al. 2024

Eng. sci. technol. j.

View full text Add to dashboard Cite

show abstract

“…Control theory can also be used for scaling [9]. Here, the controller regulates a control variable, e.g., the number of resources, to keep a (measured) variable controlled, e.g., the KPIs specified in the SLA, as close as possible to a target value within some allowed boundaries.…”

Section: Background and Related Workmentioning

confidence: 99%

Network Intelligence for NFV Scaling in Closed-Loop Architectures

et al. 2023

Self Cite

View full text Add to dashboard Cite

Characteristics like self-managing, self-adaptation, and self-organization are the main objectives of intelligent network operation. Artificial Intelligence (AI) and Machine Learning (ML) algorithms will enable future networks to operate entirely autonomously. However, current network architectures are not fully prepared to include and properly handle the promised Network Intelligence (NI). This article looks at scaling, one key Management and Orchestration (MANO) operation that allows the network to adapt to unexpected changes. We show how different scaling methods can fit the Monitor-Analyze-Plan-Execute over a shared Knowledge (MAPE-K), a well-established framework that allows architectural-based adaptation. Using a cloud-based scenario, we compare and highlight architectural differences between two prominent scaling methods, one based on Reinforcement Learning (RL) and the other based on classical control theory, showing that only the data-driven approach is adaptable enough to achieve automation. We conclude the article by pointing toward future research in autonomous, adaptive networks.

show abstract