Periodic Reporting for period 1 - DAWN4IoE (Data Aware Wireless Networks for Internet of Everything)
Période du rapport: 2017-12-01 au 2019-11-30
Internet of Everything (IoE) orchestrates the Internet of Things (IoT) into a coherent networked system. Whilst physical connectivity in IoT enables machine and device connectivity, IoE uses their data and other data sets to drive a cohesive cyber-physical system. As we accelerate into the 21st century, we are seeing increased human digital activity through the compounded effects of urbanisation and proliferation of smart devices. Beyond these statistical trends, networks are also experiencing increased data demand complexity from people and machines. Enabling real-time understanding and exploitation of these complexities is important. Over the past decade, wireless and social networks have increasingly made available meta-data with spatial components of varying resolutions. Connected network devices under the IoE paradigm, can potentially leverage on a combination of real-time data streams and other databases (i.e. geographical information system data, commercial data, census data, engineering data), to derive social context and improve the performance of underlying 4G/5G/B5G wireless network performance. Wireless networks are a fundamental cornerstone of the global digital economy and a key component in our daily lives. Each year, the mobile cellular network industry contributes 3.6% to the global GDP ($2.4 trillion), supports 10.5 million jobs, and has contributed to $336 billion of public funding.
In this project, we exploit heterogeneous big data analytics to optimize both the deployment and operations of wireless networks. We design protocols that enable future Data Aware Wireless Networks (DAWN) for enabling a new age of IoE. The proposal has been developed to address the following open issues in data driven flexible wireless systems:
• How to characterize user mobility and wireless data traffic patterns using heterogeneous data sets.
• How to infer user Quality-of-Experience (QoE) from combining data sets.
• How to use data analytics to assist network planning.
• How to use data driven techniques to optimise the network using Self-Organising-Network (SON) algorithms.
• How to optimally cache data to accelerate and optimise data storage and transmission.
The research objectives of the DAWN4IoE project are as follows:
• Develop urban propagation guided spatial-temporal filters to combine data sets and infer digital data demand patterns.
• Develop natural language processing (NLP) techniques to understand consumer experience.
• Design algorithms to integrate the new heterogeneous data analytics techniques with current state-of-the-art deployment techniques to assist HetNet planning, performance prediction, and deployment.
• Design mechanisms to integrate data analytics and drive SON algorithms.
• Design algorithms to optimally cache data leveraging on mobile edge computing (MEC).
Achieving the above objectives will provide crucial inputs for 5G/IoE data-driven flexible wireless network design and both increase network capacity by 50% and decrease operation costs by 20-30% (compared with non-data driven networks).
In this project, we exploit heterogeneous big data analytics to optimize both the deployment and operations of wireless networks. We design protocols that enable future Data Aware Wireless Networks (DAWN) for enabling a new age of IoE. The proposal has been developed to address the following open issues in data driven flexible wireless systems:
• How to characterize user mobility and wireless data traffic patterns using heterogeneous data sets.
• How to infer user Quality-of-Experience (QoE) from combining data sets.
• How to use data analytics to assist network planning.
• How to use data driven techniques to optimise the network using Self-Organising-Network (SON) algorithms.
• How to optimally cache data to accelerate and optimise data storage and transmission.
The research objectives of the DAWN4IoE project are as follows:
• Develop urban propagation guided spatial-temporal filters to combine data sets and infer digital data demand patterns.
• Develop natural language processing (NLP) techniques to understand consumer experience.
• Design algorithms to integrate the new heterogeneous data analytics techniques with current state-of-the-art deployment techniques to assist HetNet planning, performance prediction, and deployment.
• Design mechanisms to integrate data analytics and drive SON algorithms.
• Design algorithms to optimally cache data leveraging on mobile edge computing (MEC).
Achieving the above objectives will provide crucial inputs for 5G/IoE data-driven flexible wireless network design and both increase network capacity by 50% and decrease operation costs by 20-30% (compared with non-data driven networks).
To address the research and innovation (R&I) objectives, DAWN4IoE pursues a tight academic-industrial cooperation combined with an effective integration of the partners’ expertise in wireless network planning, wireless system operations, big heterogeneous data analytics, social media text analysis, multimedia data caching, and smarter cities. These skills combined are essential for obtaining fundamental understanding, acquiring new knowledge, and devising optimized solutions for flexible wireless networks. All the R&I tasks demonstrate intersectorial aspects as they are both academically challenging and industrially relevant and will contribute to the strengthening of knowledge and competitiveness of Europe in ICT.
The DAWN4IoE project is organized into five work packages (WPs). WPs 1-4 focus on the R&I objectives. WP5 implements dissemination, exploitation and public engagement activities, and project management. Each WP has a WP leader: CNR-IEIIT (WP1), RPN (WP2), UoW (WP3), WINGS-ICT (WP4), and UOW (WP5).
WP1 Progress (to date):
- quantified human population and traffic demand in urban areas
- developing clustering algorithms for wireless urban networks
- understanding the urban context
WP2 Progress (to date):
- quantified consumer experience to wireless services
- optimised network deployment using consumer data
- understanding the indoor demand context
WP3 Progress (to date):
- combined cognitive radio and LAA for joint spectrum access
- developed deep learning techniques for channel estimation and inference mitigation
WP4 Progress (to date):
- developed a cloud service framework for integrating data and services
- researched market demand for IoT/IoE in different national infrastructure areas
The DAWN4IoE project is organized into five work packages (WPs). WPs 1-4 focus on the R&I objectives. WP5 implements dissemination, exploitation and public engagement activities, and project management. Each WP has a WP leader: CNR-IEIIT (WP1), RPN (WP2), UoW (WP3), WINGS-ICT (WP4), and UOW (WP5).
WP1 Progress (to date):
- quantified human population and traffic demand in urban areas
- developing clustering algorithms for wireless urban networks
- understanding the urban context
WP2 Progress (to date):
- quantified consumer experience to wireless services
- optimised network deployment using consumer data
- understanding the indoor demand context
WP3 Progress (to date):
- combined cognitive radio and LAA for joint spectrum access
- developed deep learning techniques for channel estimation and inference mitigation
WP4 Progress (to date):
- developed a cloud service framework for integrating data and services
- researched market demand for IoT/IoE in different national infrastructure areas
DAWN4IoE provides in total 243 person-months of researcher secondments and high-quality interdisciplinary, intersectorial and international research training and knowledge sharing activities for a new generation of scientific researchers, who will benefit directly from the entrepreneurial and creative environment created by the DAWN4IoE consortium, and deliver impact at both European and international levels. It will produce a critical mass of highly-skilled professionals, who are advantaged by their intersectorial and international mobility. The Data Aware Wireless Network for Internet of Everything (DAWN4IoE) project will: (1) develop EU capacity and skills to advance big data analytics for wireless traffic and consumer experience characterization; (2) proactively optimise wireless network planning to meet new and changing demand patterns; (3) develop flexible self-organizing-network (SON) elements to learn from data and consumer experience, (4) develop data-driven mobile edge computing algorithms to dynamically balance information transfer and compute power, (5) increase EU competitiveness in data science and 5G/IoT systems and technologies; (6) develop lasting academic and industrial collaborations leading to interdisciplinary and intersectorial R&I programmes; (7) create new and exciting career prospects for all the researchers involved. Especially the ESRs and early career ERs will be a highly employable cohort of trained research scientists, engineers and managers, qualified for careers in industry, commercial organisations, advisory and regulatory bodies, or as researchers in academia and government institutes.