Abstract
WiFi Access Points (APs) can be used to offload data or computation tasks while users are commuting. However, due to APs’ limited coverage, offloading performance is heavily impacted by the users’ mobility. This work proposes to leverage human mobility to inform offloading tasks, taking a data based approach leveraging granular mobility datasets from two cities: Porto and Beijing. We define Offloading Regions (ORs) as areas where a commuter’s mobility would enable offloading, and propose an unsupervised learning methodology to extract ORs from mobility traces. Then, we characterise and analyse ORs according to offloading opportunity metrics such as type, availability, total time to offload, and offloading delay. Results show that in 50% of the trips, users spend more than 48% of the travel time inside ORs extracted according to the proposed methodology. The ability to predict the next ORs would benefit offloading orchestration. Offloading mobility predictability, although crucial, proves to be challenging, expressed by the poor predictive performance of well-known models (<inline-formula> <tex-math notation="LaTeX">$\approx $ </tex-math></inline-formula> 37% acc. for the best predictor). We show that mobility regularity properties improve predictive performance up to <inline-formula> <tex-math notation="LaTeX">$\approx $ </tex-math></inline-formula> 35%. Finally, we look into the impact of further OR extraction and prediction parameters. We show that the exploration phase length does not impact the discovery of low relevance ORs, and that both filtering low relevance OR and predicting multiple ORs increase predictability. By characterising the trade-off between mobility predictability and offloading opportunities in transit, we highlighting the need for offloading systems to adopt hybrid strategies, i.e., mixing opportunistic and predictive strategies. The conclusions and findings on offloading mobility properties are likely to generalise for varied urban scenarios given the high degree of similarity between the results obtained for the two different and independently collected mobility datasets.
Highlights
M OBILE data traffic has been growing tremendously with the increasing of the number of applications leveraging ubiquitous Internet access
Even comparing to an online Markov Chain (MC) predictor, our results show that machine learning (ML) present better performance in predicting offloading opportunities, revealing the importance of contextual information (Table IV) in offloading scenarios
This work proposes the use of granular human mobility profiles for informing offloading strategies during commuter trips
Summary
M OBILE data traffic has been growing tremendously with the increasing of the number of applications leveraging ubiquitous Internet access. Most applications cannot sustain large delays without impacting the user’s quality of experience (QoE) For this reason, it is crucial to develop mobile offloading systems that proactively take decisions on WiFi places and connectivity windows to offload data or tasks, while the users are travelling. We use mobility data to show that such a strategy is necessary and feasible to accommodate the differentiated user connectivity profiles during commute This sort of strategies will run on the user’s device and, after learning their habits of movement, will adapt and extract the best regions to perform offload. This methodology encompasses a method to establish individual offloading mobility profiles that would be part of the offloading strategies we propose — system components; and the steps that provide quantitative answers on the feasibility of such a system — system evaluation.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Transactions on Network and Service Management
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
