TY - JOUR
T1 - Federated Learning-Assisted Task Offloading Based on Feature Matching and Caching in Collaborative Device-Edge-Cloud Networks
AU - Tang, Jine
AU - Wang, Sen
AU - Yang, Song
AU - Xiang, Yong
AU - Zhou, Zhangbing
N1 - Publisher Copyright:
© 2002-2012 IEEE.
PY - 2024
Y1 - 2024
N2 - Mobile edge computing provides relatively rich computation resources for Internet-of-Things (IoT) task offloading at the edge of networks. As time goes on, user tasks present diverse requirements in function, type, dependency, urgency, etc., which makes edge servers take on dynamically diversified service features to adapt to the requirements of user tasks. Moreover, cache has been studied a lot in recent years for reducing the execution cost of related or dependent tasks. However, jointly considering which result data required to be cached and where to cache is still an intractable problem in task offloading due to dynamically diversified and sensitive features of task and edge servers for prediction. To provide more comprehensive consideration, we propose a multiple features matching scheme, coupled with federated learning-assisted collaborative caching, to enhance the efficiency of task offloading. Specifically, we first build a common features of historical tasks based FI-tree to help search for an edge server that best matches the requested task features. This helps to obtain optimal task allocation and improve offloading performance. Further, the results of tasks related to or dependent on cached results can be obtained directly through the collaborative edge cache prediction model trained by two-stage federated learning. In this way, the amount of data executed for offloaded tasks is reduced, thereby speeding up the return of final results as well as reducing the delay and energy of task execution. Meanwhile, it avoids massive transmission of task results correlated data and also protects the privacy of these data when training the prediction model. Experimental results show that our proposed method outperforms the benchmark approaches through reducing the time delay and energy consumption by at least 15.6% and 18.2%.
AB - Mobile edge computing provides relatively rich computation resources for Internet-of-Things (IoT) task offloading at the edge of networks. As time goes on, user tasks present diverse requirements in function, type, dependency, urgency, etc., which makes edge servers take on dynamically diversified service features to adapt to the requirements of user tasks. Moreover, cache has been studied a lot in recent years for reducing the execution cost of related or dependent tasks. However, jointly considering which result data required to be cached and where to cache is still an intractable problem in task offloading due to dynamically diversified and sensitive features of task and edge servers for prediction. To provide more comprehensive consideration, we propose a multiple features matching scheme, coupled with federated learning-assisted collaborative caching, to enhance the efficiency of task offloading. Specifically, we first build a common features of historical tasks based FI-tree to help search for an edge server that best matches the requested task features. This helps to obtain optimal task allocation and improve offloading performance. Further, the results of tasks related to or dependent on cached results can be obtained directly through the collaborative edge cache prediction model trained by two-stage federated learning. In this way, the amount of data executed for offloaded tasks is reduced, thereby speeding up the return of final results as well as reducing the delay and energy of task execution. Meanwhile, it avoids massive transmission of task results correlated data and also protects the privacy of these data when training the prediction model. Experimental results show that our proposed method outperforms the benchmark approaches through reducing the time delay and energy consumption by at least 15.6% and 18.2%.
KW - Mobile edge computing
KW - multiple features matching
KW - task offloading
KW - two-stage federated learning
UR - http://www.scopus.com/inward/record.url?scp=85194071160&partnerID=8YFLogxK
U2 - 10.1109/TMC.2024.3403851
DO - 10.1109/TMC.2024.3403851
M3 - Article
AN - SCOPUS:85194071160
SN - 1536-1233
VL - 23
SP - 12061
EP - 12079
JO - IEEE Transactions on Mobile Computing
JF - IEEE Transactions on Mobile Computing
IS - 12
ER -