By simulating the neurodynamics of biological brains, Spiking Neural Networks (SNNs) leverage sparse spike signal, eliminating the continuous multiply-accumulate operations of traditional Artificial Neural Networks (ANNs). Event-driven SNN processing offers significant advantages in energy efficiency and latency, making it ideal to be deployed on low-end processors. Spiking Convolutional Neural Networks (SC-NNs), which incorporate event-based processing, are increasingly employed for their power efficiency and ability to process spatio-temporal information. Unlike fully-connected networks, which rely on regular vector calculations, convolution operations present challenges for event-driven computation due to their sliding window nature.In this work, we deployed a compact 7-layer SCNN on the ARM Cortex-A9 core of PYNQ Z2 development board, using event-based acceleration. By optimizing data storage and processing sequences, we achieved efficient low-cost deployment. Offline training on the DVS128-Gesture dataset for an object recognition task yielded an accuracy of 93.40%. Following low-precision quantization and deployment, the model maintained a considerable accuracy of 92.36%. Compared to traditional periodic computation, event-based convolution processing achieved a 12.87× speedup. Furthermore, by exploiting the parallelism of feature map data storage along the channel dimension and ARM NEON instruction set, we gained an additional 2.97× speedup.

With the proliferation of IoT devices, there is an escalating demand for enhanced computing and communication capabilities. Mobile Edge Computing (MEC) addresses this need by relocating computing resources to the network edge, thereby delivering swifter and more efficient services. This paper introduces a computation offloading and energy consumption optimization framework that leverages Reconfigurable Intelligent Surfaces (RIS), Unmanned Aerial Vehicles (UAVs), and MEC. The scheme aims to maximize energy efficiency through the optimization of task allocation, RIS phase shifts, and UAV trajectories. By employing the Multi-Agent Twin Delayed Deep Deterministic Policy Gradient (MATD3) reinforcement learning algorithm, the paper further refines UAV trajectories and RIS configurations. The simulation results indicate that the proposed method surpasses the traditional Concave-Convex Procedure (CCCP) algorithm in both UAV trajectory control and RIS configuration, demonstrating quicker convergence and enhanced stability. The method proves to be adaptable to diverse environments and tasks, showcasing notable benefits in RIS-assisted interference suppression, particularly with large RIS, thereby enhancing UAV data reception rates. Additionally, MATD3 exhibits faster and smoother convergence for extended task durations and smaller RIS scenarios. Simulation results reveal that UAVs tend to move closer to RIS, with energy efficiency falling as IoT tasks increase, affirming the proposed algorithm’s high energy efficiency and effectiveness.

This paper introduce SPRCpl, an efficient compiler/toolkit for deploying Spiking Neural Network (SNN) models on multi-core neuromorphic chips. It uses "pilot running" to optimize the deployment process. It includes a front-end compiler, synapse pruning and regeneration optimizer, and a mapping tool. SPRCpl proposes a synapse pruning scheme based on spike firing statistics obtained through pilot running, dynamically reducing model size. It also presents a mapping scheme that minimizes strikes within and between clusters using spike firing statistics and multi-objective optimization. Experimental results demonstrate SPRCpl’s effectiveness in maintaining model accuracy during pruning and outperforming SpiNeMap in terms of communication count, execution time, and memory usage. It achieves lower latency, reduced power consumption, and higher throughput, making it a promising tool for SNN model deployment on multi-core neuromorphic chips.

Vehicular mobile edge computing (vMEC) and non-orthogonal multiple access (NOMA) have emerged as promising technologies for enabling low-latency and high-throughput applications in vehicular networks. In this paper, we propose a novel multi-agent deep deterministic policy gradient (MADDPG) approach for resource allocation in NOMA-based vMEC systems. Our approach leverages deep reinforcement learning (DRL) to enable vehicles to offload computation-intensive tasks to nearby edge servers, optimizing resource allocation decisions while ensuring low-latency communication. We introduce an attention mechanism within the MADDPG model to dynamically focus on relevant information from the input state and joint actions, enhancing the model’s predictive accuracy. Additionally, we propose an attention-based experience replay method to expedite network convergence. The simulation results highlight the effectiveness of multi-agent reinforcement learning (MARL) algorithms, such as MADDPG with attention, in achieving better convergence and performance in various scenarios. The influence of different model parameters, such as input data volumes, task load levels, and resource configurations, on optimization results is also evident. The decision making processes of agents are dynamic and depend on factors specific to the task and environment.

Multi-core neuromorphic hardware for spiking neural networks (SNNs) has garnered considerable attention due to its biological plausibility and energy efficiency. However, the performance of SNN applications on such hardware is constrained by the rigid architecture and interconnection among neuron cores. To enable early-stage evaluation of SNN performance on multi-core neuromorphic hardware, we introduce an accurate and scalable simulator, SpikeNC. We present the entire workflow, ranging from SNN model training to simulation, providing comprehensive insights into both model and Network-on-Chip (NoC) related statistics. Moreover, we identify a considerable amount of time wastage in the widely adopted tick-based synchronous scheme. A three-stage agent-based asynchronous scheme is proposed for fast simulation. We evaluate the performance of deep spiking neural networks (DSNNs) with various scales trained on spike-converted datasets using SpikeNC. The results demonstrate that SpikeNC achieves precise and scalable simulation for SNNs on multi-core neuromorphic hardware. Additionally, the proposed asynchronous scheme significantly reduces the simulation cycles and absolute simulation time by approximately 63 % and 56 % respectively, compared to the synchronous scheme. We also delve into the trade-offs between different design parameters and explore the influence of mapping schemes utilizing SpikeNC.

Cloud storage allows for saving files at an off-site location that is accessible through the public internet. However, cloud storage suffers from a lack of trust since employees have physical and electronic access to almost all of the data, and zero-trust security is thus essential. This paper proposes an SGX-based file hosting scheme that gives full consideration to both privacy preservation and auditability to address the aforementioned concerns. We designed a secure key exchange protocol consisting of two phases: a key generation phase and a key verification phase. Theoretical analysis and experiments indicate that the protocol can resist man in-the-middle attacks, which has been unattainable in previous studies. The experimental results show that our scheme takes little time regardless of file size and achieves solid performance in handling concurrent requests; furthermore, it is innocuous for clients, and the memory usage is acceptable.