1 February 2015 in Fluid Phase Equilibria
17 April 2025 in IEEE Transactions on Network and Service Management
The rapid advancement of artificial intelligence applications has resulted in the deployment of a growing number of deep neural networks (DNNs) on mobile devices. Given the limited computational capabilities and small battery capacity of these devices, supporting efficient DNN inference presents a significant challenge. This paper considers the joint design of DNN model partitioning and offloading under high-concurrent tasks scenarios. The primary objective is to accelerate DNN task inference and reduce computational delay. Firstly, we propose an innovative adaptive inference framework that partitions DNN models into interdependent sub-tasks through a hierarchical partitioning method. Secondly, we develop a delay prediction model based on a Random Forest (RF) regression algorithm to estimate the computational delay of each sub-task on different devices. Finally, we designed a high-performance DNN partitioning and task offloading method based on an attention mechanism-aided Soft Actor-Critic (AMSAC) algorithm. The bandwidth allocation for each user is determined by the attention mechanism based on the characteristics of the DNN tasks, and the Soft Actor-Critic algorithm is used for adaptive layer-level partitioning and offloading of the DNN model, reducing collaborative inference delay. Extensive experiments demonstrate that our proposed AMSAC algorithm effectively reduces DNN task inference latency cost and improves service quality.
9 October 2024 in IEEE Transactions on Network Science and Engineering
Edge computing has emerged as a promising paradigm to meet the increasing demands of latency-sensitive and computationally intensive applications. In this context, efficient server deployment and service placement are crucial for optimizing performance and increasing platform profit. This paper investigates the problem of server deployment and service placement in a multi-user scenario, aiming to enhance the profit of Mobile Network Operators while considering constraints related to distance thresholds, resource limitations, and connectivity requirements. We demonstrate that this problem is NP-hard. To address it, we propose a two-stage method to decouple the problem. In stage I, server deployment is formulated as a combinatorial optimization problem within the framework of a Markov Decision Process (MDP). We introduce the Server Deployment with Q-learning (SDQ) algorithm to establish a relatively stable server deployment strategy. In stage II, service placement is formulated as a constrained Integer Nonlinear Programming (INLP) problem. We present the Service Placement with Interior Barrier Method (SPIB) and Tree-based Branch-and-Bound (TDB) algorithms and theoretically prove their feasibility. For scenarios where the number of users changes dynamically, we propose the Distance-and-Utilization Balance Algorithm (DUBA). Extensive experiments validate the exceptional performance of our proposed algorithms in enhancing the profit.
24 December 2024 in IEEE Transactions on Parallel and Distributed Systems
In cloud data centers, the exponential growth of data places increasing demands on computing, storage, and network resources, especially in multi-tenant environments. While this growth is crucial for ensuring Quality of Service (QoS), it also introduces challenges such as fluctuating resource requirements and static container configurations, which can lead to resource underutilization and high energy consumption. This paper addresses online resource provisioning and efficient scheduling for multi-tenant environments, aiming to minimize energy consumption while balancing elasticity and QoS requirements. To address this, we propose a novel optimization framework that reformulates the resource provisioning problem into a more manageable form. By reducing the original multi-constraint optimization to a container placement problem, we apply the interior-point barrier method to simplify the optimization, integrating constraints directly into the objective function for efficient computation. We also introduce elasticity as a key parameter to balance energy consumption with autonomous resource scaling, ensuring that resource consolidation does not compromise system flexibility. The proposed Energy-Efficient and Elastic Resource Provisioning (EEP) framework comprises three main modules: a distributed resource management module that employs vertical partitioning and dynamic leader election for adaptive resource allocation; a prediction module using ω-step prediction for accurate resource demand forecasting; and an elastic scheduling module that dynamically adjusts to tenant scaling needs, optimizing resource allocation and minimizing energy consumption. Extensive experiments across diverse cloud scenarios demonstrate that the EEP framework significantly improves energy efficiency and resource utilization compared to established baselines, supporting sustainable cloud management practices.
23 February 2026 in IEEE Internet of Things Journal
In collaborative inference scenarios, semantic communication replaces raw data transmission by conveying task-oriented semantic features to improve bandwidth efficiency. However, under noisy wireless channels, the combined effects of semantic compression distortion and channel noise lead to severe information loss, resulting in degraded inference accuracy. To address this issue, this article proposes a multiscale semantic compression collaborative inference (MSCCI) framework that achieves efficient, stable inference performance under high compression ratios (CRs) and elevated noise levels. Specifically, a UNet-based encoder extracts multiscale semantic features on an IoT device. These features are then integrated into a unified stream using a novel semantic fusion compression strategy, thereby substantially reducing communication overhead. The edge server decoder decompresses features and recovers image semantics via progressive upsampling and multiscale semantic restoration. For noisy wireless channels, the framework incorporates squeeze-and-excitation (SE) attention for dynamic feature channel weighting and residual connections for enhanced low-SNR robustness. Experimental results demonstrate that our collaborative inference framework for semantic communication outperforms state-of-the-art algorithms, and the approach’s effectiveness and robustness are verified across various channel conditions.