Periodic Reporting for period 1 - QoSIoTSmartCities (Quality of Service for the Internet of Things in Smart Cities via Predictive Networks)
Reporting period: 2019-04-01 to 2021-03-31
Fifth Generation (5G) cellular systems are already being deployed, which will make an enormous impact on our lives: These systems enable a variety of applications, such as remote surgery (as part of the Tactile Internet), augmented (virtual) reality, industrial and vehicular automation, autonomous driving, enhanced mobile broadband as well as Internet of Things (IoT). These applications will become an important part of our digitally connected lives and form the new infrastructure of the smart cities of the new future.
Among these applications, IoT appears as a key enabler of technologies that will be deployed in smart cities. Applications of IoT range from smart bins that indicate to the municipality when they are full, smart lamp posts that adjust their lighting in response to the needs of pedestrians and cars while reducing energy consumption, and a plethora of other services that smart cities will provide to their dwellers in smart hospitals, homes, factories and transportation. While 5G provides the necessary initial infrastructure world-wide for these diverse services to take off, the evolution towards Sixth Generation (6G) networks brings new challenges, especially in regard to Quality of Service (QoS), which refers to a diverse set of requirements that must be satisfied by the telecommunication network in order to deliver a smooth experience to its human users.
The goal of this project is to enable the delivery of Quality of Service (QoS) for the Internet of Things (IoT) in smart cities. Since seventy-five billion IoT devices are expected to be on the Internet by the year 2025, satisfying QoS for IoT is extremely challenging, as the problems of scalability, latency, reliability, energy efficiency and mobility must be solved jointly.
Towards this goal, the specific objectives of this project are (1) to develop forecasting algorithms in order to predict IoT traffic on the Internet, (2) to develop predictive QoS optimization algorithms targeted at IoT, and (3) to build a scalable network simulation of IoT devices in a representative smart city model.
Among these applications, IoT appears as a key enabler of technologies that will be deployed in smart cities. Applications of IoT range from smart bins that indicate to the municipality when they are full, smart lamp posts that adjust their lighting in response to the needs of pedestrians and cars while reducing energy consumption, and a plethora of other services that smart cities will provide to their dwellers in smart hospitals, homes, factories and transportation. While 5G provides the necessary initial infrastructure world-wide for these diverse services to take off, the evolution towards Sixth Generation (6G) networks brings new challenges, especially in regard to Quality of Service (QoS), which refers to a diverse set of requirements that must be satisfied by the telecommunication network in order to deliver a smooth experience to its human users.
The goal of this project is to enable the delivery of Quality of Service (QoS) for the Internet of Things (IoT) in smart cities. Since seventy-five billion IoT devices are expected to be on the Internet by the year 2025, satisfying QoS for IoT is extremely challenging, as the problems of scalability, latency, reliability, energy efficiency and mobility must be solved jointly.
Towards this goal, the specific objectives of this project are (1) to develop forecasting algorithms in order to predict IoT traffic on the Internet, (2) to develop predictive QoS optimization algorithms targeted at IoT, and (3) to build a scalable network simulation of IoT devices in a representative smart city model.
In the first part of this project, first, we carried out a comparative study of forecasting schemes for IoT Device Traffic in Machine-to-Machine Communication. Second, we developed a novel end-to-end trainable feature selection-forecasting architecture targeted at the Internet of Things. Third, we derived information-theoretic bounds for IoT traffic, and demonstrated the predictability of IoT traffic against information-theoretic bounds. In the second part of this project, we developed a novel predictive Quality of Service (QoS) routing algorithm for software-defined networks. Our work has incorporated the constraints for all of the key traffic types (namely Ultra-Reliable Low Latency Communication (URLLC), enhanced Mobile Broadband (eMBB), and massive Machine-Type Communication (mMTC)). In the third part of this project, we built a a multi-cell smart city simulator, which we have named LEAN, for the Internet of Things.
The results of this project have been widely disseminated via the following activities: (1) conference and journal publications, (2) an Internet of Things course, (3) organization of a workshop on the applications of Machine Learning/Artificial Intelligence to Networking, (4) organization of a Technology Day, (5) outreach activities to the general public, including media interviews, press releases, media coverage as well as invited talks.
The results of this project have been widely disseminated via the following activities: (1) conference and journal publications, (2) an Internet of Things course, (3) organization of a workshop on the applications of Machine Learning/Artificial Intelligence to Networking, (4) organization of a Technology Day, (5) outreach activities to the general public, including media interviews, press releases, media coverage as well as invited talks.
This project has achieved advances in the applications of Artificial Intelligence to telecommunication networks. Telecommunication networks based on Artificial Intelligence are expected to significantly transform the digital smart city landscape as they will be able to support a much larger number of simultaneous traffic flows of different types (latency-critical data, e.g. as in remote surgery; video flows; and massive IoT flows). Hence, such technology is expected to lower the cost of telecommunication in the near future. Lowering such costs will become important as the data from heterogeneous applications continue to grow exponentially.