Energy-Efficient DNN Partitioning and Offloading for Task Completion Rate Maximization in Multiuser Edge Intelligence
نویسندگان
چکیده
Deep Neural Network (DNN) has become an essential technology for edge intelligence. Due to significant resource and energy requirements large-scale DNNs’ inference, executing them directly on energy-constrained Internet of Things (IoT) devices is impractical. DNN partitioning provides a feasible solution this problem by offloading some layers execute the server. However, resources servers are also typically limited. An resource-constrained optimization generated in such realistic environment. Motivated this, we investigate multiuser environment, which considered intractable Mixed-Integer Nonlinear Problem (MINLP). We decompose into two subproblems propose Energy-Efficient Partitioning Offloading (EEDPO) strategy solve it polynomial time based minimum cut/maximum flow theorem dynamic programming. Finally, test impact constraint, type, device number performance EEDPO. Simulation results models demonstrate that proposed can significantly improve inference task completion rate compared other methods.
منابع مشابه
Asynchronous Mobile-Edge Computation Offloading: Energy-Efficient Resource Management
Mobile-edge computation offloading (MECO) is an emerging technology for enhancing mobiles’ computation capabilities and prolonging their battery lives, by offloading intensive computation from mobiles to nearby servers such as base stations. In this paper, we study the energy-efficient resourcemanagement policy for the asynchronous MECO system, where the mobiles have heterogeneous inputdata arr...
متن کاملComputation Rate Maximization for Wireless Powered Mobile-Edge Computing with Binary Computation Offloading
Finite battery lifetime and low computing capability of size-constrained wireless devices (WDs) have been longstanding performance limitations of many low-power wireless networks, e.g., wireless sensor networks (WSNs) and Internet of Things (IoT). The recent development of radio frequency (RF) based wireless power transfer (WPT) and mobile edge computing (MEC) technologies provide promising sol...
متن کاملEnergy Efficient Adaptive Offloading For Mobile Cloud Computing Using Optimal Partitioning Algorithm
Mobile Cloud Computing is an emerging technology that integrates the cloud computing concept into the mobile environment. The limitations of mobile devices such as its storage capacity, battery lifetime can be overcome with the offloading of applications that is migration of large or complex computation to servers or cloud. This paper presents the adaptive offloading of the tasks using the opti...
متن کاملConvex Approximated Weighted Sum-Rate Maximization for Multicell Multiuser OFDM
This letter considers the weighted sum-rate maximization (WSRMax) problem in downlink multicell multiuser orthogonal frequency-division multiplexing system. The WSRMax problem under per base station transmit power constraint is known to be NP-hard, and the optimal solution is computationally very expensive. We propose two lesscomplex suboptimal convex approximated solutions which are based on s...
متن کاملDesign and Evaluation of a Method for Partitioning and Offloading Web-based Applications in Mobile Systems with Bandwidth Constraints
Computation offloading is known to be among the effective solutions of running heavy applications on smart mobile devices. However, irregular changes of a mobile data rate have direct impacts on code partitioning when offloading is in progress. It is believed that once a rate-adaptive partitioning performed, the replication of such substantial processes due to bandwidth fluctuation can be avoid...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Wireless Communications and Mobile Computing
سال: 2023
ISSN: ['1530-8669', '1530-8677']
DOI: https://doi.org/10.1155/2023/3835297