Real-time object detection is significant for industrial and research fields. On edge devices, a giant model is difficult to achieve the real-time detecting requirement and a lightweight model built from a large number of the depth-wise separable convolutional could not achieve the sufficient accuracy. We introduce a new lightweight convolutional technique, GSConv, to lighten the model but maintain the accuracy. The GSConv accomplishes an excellent trade-off between the accuracy and speed. Furthermore, we provide a design suggestion based on the GSConv, Slim-Neck (SNs), to achieve a higher computational cost-effectiveness of the real-time detectors. The effectiveness of the SNs was robustly demonstrated in over twenty sets comparative experiments. In particular, the real-time detectors of ameliorated by the SNs obtain the state-of-the-art (70.9% AP50 for the SODA10M at a speed of ~ 100FPS on a Tesla T4) compared with the baselines. Code is available at https://github.com/alanli1997/slim-neck-by-gsconv
Edge computing enables smart IoT-based systems via concurrent and continuous execution of latency-sensitive machine learning (ML) applications. These edge-based machine learning systems are often battery-powered (i.e., energy-limited). They use heterogeneous resources with diverse computing performance (e.g., CPU, GPU, and/or FPGAs) to fulfill the latency constraints of ML applications. The challenge is to allocate user requests for different ML applications on the Heterogeneous Edge Computing Systems (HEC) with respect to both the energy and latency constraints of these systems. To this end, we study and analyze resource allocation solutions that can increase the on-time task completion rate while considering the energy constraint. Importantly, we investigate edge-friendly (lightweight) multi-objective mapping heuristics that do not become biased toward a particular application type to achieve the objectives; instead, the heuristics consider "fairness" across the concurrent ML applications in their mapping decisions. Performance evaluations demonstrate that the proposed heuristic outperforms widely-used heuristics in heterogeneous systems in terms of the latency and energy objectives, particularly, at low to moderate request arrival rates. We observed 8.9% improvement in on-time task completion rate and 12.6% in energy-saving without imposing any significant overhead on the edge system.
In recent years, deep learning models have become ubiquitous in industry and academia alike. Deep neural networks can solve some of the most complex pattern-recognition problems today, but come with the price of massive compute and memory requirements. This makes the problem of deploying such large-scale neural networks challenging in resource-constrained mobile edge computing platforms, specifically in mission-critical domains like surveillance and healthcare. To solve this, a promising solution is to split resource-hungry neural networks into lightweight disjoint smaller components for pipelined distributed processing. At present, there are two main approaches to do this: semantic and layer-wise splitting. The former partitions a neural network into parallel disjoint models that produce a part of the result, whereas the latter partitions into sequential models that produce intermediate results. However, there is no intelligent algorithm that decides which splitting strategy to use and places such modular splits to edge nodes for optimal performance. To combat this, this work proposes a novel AI-driven online policy, SplitPlace, that uses Multi-Armed-Bandits to intelligently decide between layer and semantic splitting strategies based on the input task's service deadline demands. SplitPlace places such neural network split fragments on mobile edge devices using decision-aware reinforcement learning for efficient and scalable computing. Moreover, SplitPlace fine-tunes its placement engine to adapt to volatile environments. Our experiments on physical mobile-edge environments with real-world workloads show that SplitPlace can significantly improve the state-of-the-art in terms of average response time, deadline violation rate, inference accuracy, and total reward by up to 46, 69, 3 and 12 percent respectively.
Insects are the most important global pollinator of crops and play a key role in maintaining the sustainability of natural ecosystems. Insect pollination monitoring and management are therefore essential for improving crop production and food security. Computer vision facilitated pollinator monitoring can intensify data collection over what is feasible using manual approaches. The new data it generates may provide a detailed understanding of insect distributions and facilitate fine-grained analysis sufficient to predict their pollination efficacy and underpin precision pollination. Current computer vision facilitated insect tracking in complex outdoor environments is restricted in spatial coverage and often constrained to a single insect species. This limits its relevance to agriculture. Therefore, in this article we introduce a novel system to facilitate markerless data capture for insect counting, insect motion tracking, behaviour analysis and pollination prediction across large agricultural areas. Our system is comprised of edge computing multi-point video recording, offline automated multispecies insect counting, tracking and behavioural analysis. We implement and test our system on a commercial berry farm to demonstrate its capabilities. Our system successfully tracked four insect varieties, at nine monitoring stations within polytunnels, obtaining an F-score above 0.8 for each variety. The system enabled calculation of key metrics to assess the relative pollination impact of each insect variety. With this technological advancement, detailed, ongoing data collection for precision pollination becomes achievable. This is important to inform growers and apiarists managing crop pollination, as it allows data-driven decisions to be made to improve food production and food security.
The design of effective online caching policies is an increasingly important problem for content distribution networks, online social networks and edge computing services, among other areas. This paper proposes a new algorithmic toolbox for tackling this problem through the lens of \emph{optimistic} online learning. We build upon the Follow-the-Regularized-Leader (FTRL) framework, which is developed further here to include predictions for the file requests, and we design online caching algorithms for bipartite networks with pre-reserved or dynamic storage subject to time-average budget constraints. The predictions are provided by a content recommendation system that influences the users viewing activity and hence can naturally reduce the caching network's uncertainty about future requests. We also extend the framework to learn and utilize the best request predictor in cases where many are available. We prove that the proposed {optimistic} learning caching policies can achieve \emph{sub-zero} performance loss (regret) for perfect predictions, and maintain the sub-linear regret bound $O(\sqrt T)$, which is the best achievable bound for policies that do not use predictions, even for arbitrary-bad predictions. The performance of the proposed algorithms is evaluated with detailed trace-driven numerical tests.
With the increasing demand for deep learning models on mobile devices, splitting neural network computation between the device and a more powerful edge server has become an attractive solution. However, existing split computing approaches often underperform compared to a naive baseline of remote computation on compressed data. Recent studies propose learning compressed representations that contain more relevant information for supervised downstream tasks, showing improved tradeoffs between compressed data size and supervised performance. However, existing evaluation metrics only provide an incomplete picture of split computing. This study introduces supervised compression for split computing (SC2) and proposes new evaluation criteria: minimizing computation on the mobile device, minimizing transmitted data size, and maximizing model accuracy. We conduct a comprehensive benchmark study using 10 baseline methods, three computer vision tasks, and over 180 trained models, and discuss various aspects of SC2. We also release sc2bench, a Python package for future research on SC2. Our proposed metrics and package will help researchers better understand the tradeoffs of supervised compression in split computing.
The design of effective online caching policies is an increasingly important problem for content distribution networks, online social networks and edge computing services, among other areas. This paper proposes a new algorithmic toolbox for tackling this problem through the lens of optimistic online learning. We build upon the Follow-the-Regularized-Leader (FTRL) framework which is developed further here to include predictions for the file requests, and we design online caching algorithms for bipartite networks with fixed-size caches or elastic leased caches subject to time-average budget constraints. The predictions are provided by a content recommendation system that influences the users viewing activity, and hence can naturally reduce the caching network's uncertainty about future requests. We prove that the proposed optimistic learning caching policies can achieve sub-zero performance loss (regret) for perfect predictions, and maintain the best achievable regret bound $O(\sqrt T)$ even for arbitrary-bad predictions. The performance of the proposed algorithms is evaluated with detailed trace-driven numerical tests.
Federated learning (FL) has been increasingly considered to preserve data training privacy from eavesdropping attacks in mobile edge computing-based Internet of Thing (EdgeIoT). On the one hand, the learning accuracy of FL can be improved by selecting the IoT devices with large datasets for training, which gives rise to a higher energy consumption. On the other hand, the energy consumption can be reduced by selecting the IoT devices with small datasets for FL, resulting in a falling learning accuracy. In this paper, we formulate a new resource allocation problem for privacy-persevering EdgeIoT to balance the learning accuracy of FL and the energy consumption of the IoT device. We propose a new federated learning-enabled twin-delayed deep deterministic policy gradient (FL-DLT3) framework to achieve the optimal accuracy and energy balance in a continuous domain. Furthermore, long short term memory (LSTM) is leveraged in FL-DLT3 to predict the time-varying network state while FL-DLT3 is trained to select the IoT devices and allocate the transmit power. Numerical results demonstrate that the proposed FL-DLT3 achieves fast convergence (less than 100 iterations) while the FL accuracy-to-energy consumption ratio is improved by 51.8% compared to existing state-of-the-art benchmark.
While lots of research has been conducted on the architecture of Industrial Internet of Things (IIoT) systems, concepts of structuring their development processes are missing. Therefore, we propose a holistic approach supporting organizations in rapid development of IIoT systems. It includes the structuring of the development process into multiple projects sharing project conventions. Utilizing a single configurable build script for all projects, our goal is to make the integration of code from various projects into broader IIoT systems easy and the systems decomposable with minimal effort.
Knowledge Distillation is a technique which aims to utilize dark knowledge to compress and transfer information from a vast, well-trained neural network (teacher model) to a smaller, less capable neural network (student model) with improved inference efficiency. This approach of distilling knowledge has gained popularity as a result of the prohibitively complicated nature of such cumbersome models for deployment on edge computing devices. Generally, the teacher models used to teach smaller student models are cumbersome in nature and expensive to train. To eliminate the necessity for a cumbersome teacher model completely, we propose a simple yet effective knowledge distillation framework that we termed Dynamic Rectification Knowledge Distillation (DR-KD). Our method transforms the student into its own teacher, and if the self-teacher makes wrong predictions while distilling information, the error is rectified prior to the knowledge being distilled. Specifically, the teacher targets are dynamically tweaked by the agency of ground-truth while distilling the knowledge gained from traditional training. Our proposed DR-KD performs remarkably well in the absence of a sophisticated cumbersome teacher model and achieves comparable performance to existing state-of-the-art teacher-free knowledge distillation frameworks when implemented by a low-cost dynamic mannered teacher. Our approach is all-encompassing and can be utilized for any deep neural network training that requires categorization or object recognition. DR-KD enhances the test accuracy on Tiny ImageNet by 2.65% over prominent baseline models, which is significantly better than any other knowledge distillation approach while requiring no additional training costs.
Generative Adversarial Networks (GAN) are cutting-edge algorithms for generating new data samples based on the learned data distribution. However, its performance comes at a significant cost in terms of computation and memory requirements. In this paper, we proposed an HW/SW co-design approach for training quantized deconvolution GAN (QDCGAN) implemented on FPGA using a scalable streaming dataflow architecture capable of achieving higher throughput versus resource utilization trade-off. The developed accelerator is based on an efficient deconvolution engine that offers high parallelism with respect to scaling factors for GAN-based edge computing. Furthermore, various precisions, datasets, and network scalability were analyzed for low-power inference on resource-constrained platforms. Lastly, an end-to-end open-source framework is provided for training, implementation, state-space exploration, and scaling the inference using Vivado high-level synthesis for Xilinx SoC-FPGAs, and a comparison testbed with Jetson Nano.
Beam selection for millimeter-wave links in a vehicular scenario is a challenging problem, as an exhaustive search among all candidate beam pairs cannot be assuredly completed within short contact times. We solve this problem via a novel expediting beam selection by leveraging multimodal data collected from sensors like LiDAR, camera images, and GPS. We propose individual modality and distributed fusion-based deep learning (F-DL) architectures that can execute locally as well as at a mobile edge computing center (MEC), with a study on associated tradeoffs. We also formulate and solve an optimization problem that considers practical beam-searching, MEC processing and sensor-to-MEC data delivery latency overheads for determining the output dimensions of the above F-DL architectures. Results from extensive evaluations conducted on publicly available synthetic and home-grown real-world datasets reveal 95% and 96% improvement in beam selection speed over classical RF-only beam sweeping, respectively. F-DL also outperforms the state-of-the-art techniques by 20-22% in predicting top-10 best beam pairs.
Workflow scheduling is a long-studied problem in parallel and distributed computing (PDC), aiming to efficiently utilize compute resources to meet user's service requirements. Recently proposed scheduling methods leverage the low response times of edge computing platforms to optimize application Quality of Service (QoS). However, scheduling workflow applications in mobile edge-cloud systems is challenging due to computational heterogeneity, changing latencies of mobile devices and the volatile nature of workload resource requirements. To overcome these difficulties, it is essential, but at the same time challenging, to develop a long-sighted optimization scheme that efficiently models the QoS objectives. In this work, we propose MCDS: Monte Carlo Learning using Deep Surrogate Models to efficiently schedule workflow applications in mobile edge-cloud computing systems. MCDS is an Artificial Intelligence (AI) based scheduling approach that uses a tree-based search strategy and a deep neural network-based surrogate model to estimate the long-term QoS impact of immediate actions for robust optimization of scheduling decisions. Experiments on physical and simulated edge-cloud testbeds show that MCDS can improve over the state-of-the-art methods in terms of energy consumption, response time, SLA violations and cost by at least 6.13, 4.56, 45.09 and 30.71 percent respectively.
Building a fault-tolerant edge system that can quickly react to node overloads or failures is challenging due to the unreliability of edge devices and the strict service deadlines of modern applications. Moreover, unnecessary task migrations can stress the system network, giving rise to the need for a smart and parsimonious failure recovery scheme. Prior approaches often fail to adapt to highly volatile workloads or accurately detect and diagnose faults for optimal remediation. There is thus a need for a robust and proactive fault-tolerance mechanism to meet service level objectives. In this work, we propose PreGAN, a composite AI model using a Generative Adversarial Network (GAN) to predict preemptive migration decisions for proactive fault-tolerance in containerized edge deployments. PreGAN uses co-simulations in tandem with a GAN to learn a few-shot anomaly classifier and proactively predict migration decisions for reliable computing. Extensive experiments on a Raspberry-Pi based edge environment show that PreGAN can outperform state-of-the-art baseline methods in fault-detection, diagnosis and classification, thus achieving high quality of service. PreGAN accomplishes this by 5.1% more accurate fault detection, higher diagnosis scores and 23.8% lower overheads compared to the best method among the considered baselines.
Machine learning (ML) is expected to play a major role in 5G edge computing. Various studies have demonstrated that ML is highly suitable for optimizing edge computing systems as rapid mobility and application-induced changes occur at the edge. For ML to provide the best solutions, it is important to continually train the ML models to include the changing scenarios. The sudden changes in data distributions caused by changing scenarios (e.g., 5G base station failures) is referred to as concept drift and is a major challenge to continual learning. The ML models can present high error rates while the drifts take place and the errors decrease only after the model learns the distributions. This problem is more pronounced in a distributed setting where multiple ML models are being used for different heterogeneous datasets and the final model needs to capture all concept drifts. In this paper, we show that using Attention in Federated Learning (FL) is an efficient way of handling concept drifts. We use a 5G network traffic dataset to simulate concept drift and test various scenarios. The results indicate that Attention can significantly improve the concept drift handling capability of FL.
Influenced by the great success of deep learning via cloud computing and the rapid development of edge chips, research in artificial intelligence (AI) has shifted to both of the computing paradigms, i.e., cloud computing and edge computing. In recent years, we have witnessed significant progress in developing more advanced AI models on cloud servers that surpass traditional deep learning models owing to model innovations (e.g., Transformers, Pretrained families), explosion of training data and soaring computing capabilities. However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed. In this survey, we conduct a systematic review for both cloud and edge AI. Specifically, we are the first to set up the collaborative learning mechanism for cloud and edge modeling with a thorough review of the architectures that enable such mechanism. We also discuss potentials and practical experiences of some on-going advanced edge AI topics including pretraining models, graph neural networks and reinforcement learning. Finally, we discuss the promising directions and challenges in this field.
Edge computing devices inherently face tight resource constraints, which is especially apparent when deploying Deep Neural Networks (DNN) with high memory and compute demands. FPGAs are commonly available in edge devices. Since these reconfigurable circuits can achieve higher throughput and lower power consumption than general purpose processors, they are especially well-suited for DNN acceleration. However, existing solutions for designing FPGA-based DNN accelerators for edge devices come with high development overheads, given the cost of repeated FPGA synthesis passes, reimplementation in a Hardware Description Language (HDL) of the simulated design, and accelerator system integration. In this paper we propose SECDA, a new hardware/software co-design methodology to reduce design time of optimized DNN inference accelerators on edge devices with FPGAs. SECDA combines cost-effective SystemC simulation with hardware execution, streamlining design space exploration and the development process via reduced design evaluation time. As a case study, we use SECDA to efficiently develop two different DNN accelerator designs on a PYNQ-Z1 board, a platform that includes an edge FPGA. We quickly and iteratively explore the system's hardware/software stack, while identifying and mitigating performance bottlenecks. We evaluate the two accelerator designs with four common DNN models, achieving an average performance speedup across models of up to 3.5$\times$ with a 2.9$\times$ reduction in energy consumption over CPU-only inference. Our code is available at https://github.com/gicLAB/SECDA
There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors. However, full-scale deep neural networks are often too resource-intensive in terms of energy and storage. As a result, the bulk part of the machine learning operation is therefore often carried out on an edge server, where the data is compressed and transmitted. However, compressing data (such as images) leads to transmitting information irrelevant to the supervised task. Another popular approach is to split the deep network between the device and the server while compressing intermediate features. To date, however, such split computing strategies have barely outperformed the aforementioned naive data compression baselines due to their inefficient approaches to feature compression. This paper adopts ideas from knowledge distillation and neural image compression to compress intermediate feature representations more efficiently. Our supervised compression approach uses a teacher model and a student model with a stochastic bottleneck and learnable prior for entropy coding (Entropic Student). We compare our approach to various neural image and feature compression baselines in three vision tasks and found that it achieves better supervised rate-distortion performance while maintaining smaller end-to-end latency. We furthermore show that the learned feature representations can be tuned to serve multiple downstream tasks.
Federated Deep Learning (FDL) is helping to realize distributed machine learning in the Internet of Vehicles (IoV). However, FDL's global model needs multiple clients to upload learning model parameters, thus still existing unavoidable communication overhead and data privacy risks. The recently proposed Swarm Learning (SL) provides a decentralized machine-learning approach uniting edge computing and blockchain-based coordination without the need for a central coordinator. This paper proposes a Swarm-Federated Deep Learning framework in the IoV system (IoV-SFDL) that integrates SL into the FDL framework. The IoV-SFDL organizes vehicles to generate local SL models with adjacent vehicles based on the blockchain empowered SL, then aggregates the global FDL model among different SL groups with a proposed credibility weights prediction algorithm. Extensive experimental results demonstrate that compared with the baseline frameworks, the proposed IoV-SFDL framework achieves a 16.72% reduction in edge-to-global communication overhead while improving about 5.02% in model performance with the same training iterations.
Tiny Machine Learning (TML) is a new research area whose goal is to design machine and deep learning techniques able to operate in Embedded Systems and IoT units, hence satisfying the severe technological constraints on memory, computation, and energy characterizing these pervasive devices. Interestingly, the related literature mainly focused on reducing the computational and memory demand of the inference phase of machine and deep learning models. At the same time, the training is typically assumed to be carried out in Cloud or edge computing systems (due to the larger memory and computational requirements). This assumption results in TML solutions that might become obsolete when the process generating the data is affected by concept drift (e.g., due to periodicity or seasonality effect, faults or malfunctioning affecting sensors or actuators, or changes in the users' behavior), a common situation in real-world application scenarios. For the first time in the literature, this paper introduces a Tiny Machine Learning for Concept Drift (TML-CD) solution based on deep learning feature extractors and a k-nearest neighbors classifier integrating a hybrid adaptation module able to deal with concept drift affecting the data-generating process. This adaptation module continuously updates (in a passive way) the knowledge base of TML-CD and, at the same time, employs a Change Detection Test to inspect for changes (in an active way) to quickly adapt to concept drift by removing the obsolete knowledge. Experimental results on both image and audio benchmarks show the effectiveness of the proposed solution, whilst the porting of TML-CD on three off-the-shelf micro-controller units shows the feasibility of what is proposed in real-world pervasive systems.