Search for: All records

Federated learning at edge systems not only mitigates privacy concerns by keeping data localized but also leverages edge computing resources to enable real-time AI inference and decision-making. In a blockchain-based federated learning framework over edge clouds, edge servers as clients can contribute private data or computing resources to the overall training or mining task for secure model aggregation. To overcome the impractical assumption that edge servers will voluntarily join training or mining, it is crucial to design an incentive mechanism that motivates edge servers to achieve optimal training and mining outcomes. In this paper, we investigate the incentive mechanism design for a semi-asynchronous blockchain-based federated edge learning system. We model the resource pricing mechanism among edge servers and task publishers as a Stackelberg game and prove the existence and uniqueness of a Nash equilibrium in such a game. We then propose an iterative algorithm based on the Alternating Direction Method of Multipliers (ADMM) to achieve the optimal strategies for each participating edge server. Finally, our simulation results verify the convergence and efficiency of our proposed scheme. 

Users on edge generate deep inference requests continuously over time. Mobile/edge devices located near users can undertake the computation of inference locally for users, e.g., the embedded edge device on an autonomous vehicle. Due to limited computing resources on one mobile/edge device, it may be challenging to process the inference requests from users with high throughput. An attractive solution is to (partially) offload the computation to a remote device in the network. In this paper, we examine the existing inference execution solutions across local and remote devices and propose an adaptive scheduler, a BPS scheduler, for continuous deep inference on collaborative edge intelligence. By leveraging data parallel, neurosurgeon, reinforcement learning techniques, BPS can boost the overall inference performance by up to 8.2× over the baseline schedulers. A lightweight compressor, FF, specialized in compressing intermediate output data for neurosurgeon, is proposed and integrated into the BPS scheduler. FF exploits the operating character of convolutional layers and utilizes efficient approximation algorithms. Compared to existing compression methods, FF achieves up to 86.9% lower accuracy loss and up to 83.6% lower latency overhead. 

Deep neural network (DNN) inference poses unique challenges in serving computational requests due to high request intensity, concurrent multi-user scenarios, and diverse heterogeneous service types. Simultaneously, mobile and edge devices provide users with enhanced computational capabilities, enabling them to utilize local resources for deep inference processing. Moreover, dynamic inference techniques allow content-based computational cost selection per request. This paper presents Dystri, an innovative framework devised to facilitate dynamic inference on distributed edge infrastructure, thereby accommodating multiple heterogeneous users. Dystri offers a broad applicability in practical environments, encompassing heterogeneous device types, DNN-based applications, and dynamic inference techniques, surpassing the state-of-the-art (SOTA) approaches. With distributed controllers and a global coordinator, Dystri allows per-request, per-user adjustments of quality-of-service, ensuring instantaneous, flexible, and discrete control. The decoupled workflows in Dystri naturally support user heterogeneity and scalability, addressing crucial aspects overlooked by existing SOTA works. Our evaluation involves three multi-user, heterogeneous DNN inference service platforms deployed on distributed edge infrastructure, encompassing seven DNN applications. Results show Dystri achieves near-zero deadline misses and excels in adapting to varying user numbers and request intensities. Dystri outperforms baselines with accuracy improvement up to 95 ×.