Data Processing Latency Research Articles

Evaluating the Possibilities and Difficulties of Edge Computing's Real-time Data Processing

This study examines real-time data processing within the framework of edge computing, evaluating its importance, difficulties, and uses. It incorporates a thorough methodology that includes critical analysis, experimental findings, and a review of the literature. The goals are to comprehend the fundamentals of edge computing, assess its applicability to real-time data processing, and pinpoint its advantages and disadvantages. Results highlight how important edge computing is for lowering latency in data processing, saving bandwidth on networks, and improving scalability—especially for AR/VR and driverless car applications.

Optimization model for vehicular network data queries in edge environments

As the Internet of Vehicles advances, the demand for timely data acquisition by vehicle users continues to escalate, albeit confronted with the challenge of excessive data retrieval latency. The emergence of edge computing provides technical support for the development of vehicular networks by caching data in advance to reduce data acquisition latency. Therefore, how to effectively cache and query data becomes a key issue in addressing the timeliness of data acquisition in vehicular networks. In this paper, we investigate an efficient query optimization model to minimize data acquisition latency. Firstly, based on the distribution of data query frequencies across different servers, we propose an edge collaborative caching strategy using a tabu search algorithm. This strategy prioritizes high-traffic data by finding two optimal storage nodes for each high-traffic data in descending order of data popularity, ensuring a backup within the collaborative domain for each data segment. This not only reduces data transmission latency between nodes during task execution but also prevents single-point failures. Secondly, we deploy cuckoo filters on edge nodes to enable rapid localization of cached data nodes when users query data, thus reducing data processing latency. Finally, simulation results demonstrate that the proposed query optimization model outperforms other schemes in terms of average data query latency.

Performance Testing Techniques for Live TV Streaming on STBs

In the realm of live TV streaming, performance testing is critical to ensure seamless delivery and optimal user experience on Set-Top Boxes (STBs). This paper presents a comprehensive exploration of performance testing techniques tailored for live TV streaming on STBs, focusing on methodologies, challenges, and best practices. With the growing demand for high-quality, uninterrupted live TV content, effective performance testing becomes imperative to address issues related to latency, buffering, and overall system reliability. The study begins with an overview of the unique performance challenges associated with live TV streaming on STBs. Unlike on-demand streaming, live TV requires real-time data processing and minimal latency to deliver a continuous viewing experience. The paper categorizes performance testing into several key areas: network performance, system resource utilization, and user experience. Network performance testing evaluates the efficiency of data transmission across various network conditions. Techniques such as bandwidth measurement, latency analysis, and jitter assessment are employed to simulate different network scenarios and determine their impact on streaming quality. These tests help in identifying bottlenecks and optimizing network configurations to support smooth streaming.

Edge2LoRa: Enabling edge computing on long-range wide-area Internet of Things

Long-Power Wide Area Networks (LPWAN) is a low-cost solution to deploy very-large scale Internet of Things (IoT) infrastructures with minimal requirements following a classic producer/consumer model. Inevitably such deployments will require a shift towards low-latency, distributed and collaborative data aggregation models. The cloud edge computing continuum (CECC) has been proposed as an evolution of the traditional central ultra-high-end processing cloud into a continuum of collaborative processing elements distributed from the cloud to the network edge. Until today, incorporating existing centralized and monolithic LPWAN architectures in the CECC faces multiple security-related implications. We propose Edge2LoRa, a complete secure solution to incorporate LPWAN architectures in CECC enabling faster data processing while reducing the transmission of sensitive data. It improves network performance through data pre-processing, traffic flow optimization, and real-time local analysis. Edge2LoRa gradually transform existing LPWAN deployments into agile and versatile infrastructures that enable the seamless and efficient processing of data throughout the CECC while guaranteeing service continuity and full-backwards compatibility. We implement Edge2LoRa in hardware compliant with the Things Stack and the LoRaWAN v1.0.4 and v1.1. We evaluate the performance in terms of networking and computing resource utilization, quality of service and security. The results provide a clear indication of the improvements to public and private LoRaWAN infrastructures without any disruption or service degradation for existing legacy services. In public LoRaWAN deployments where large-scale IoT data streams drive big data analytics, we demonstrate core network bandwidth usage reductions of up to 90% and data processing latency improvements by a ×10 factor.

Energy efficient reliable data transmission for optimizing IoT data transmission in smart city

The rapid proliferation of the internet of things (IoT) technology has significantly transformed urban landscapes, giving rise to smart city frameworks that leverage interconnected devices for enhanced efficiency and functionality. In these environments, vast amounts of data are generated by diverse sensors and devices, necessitating advanced strategies for effective data collection and transmission. This paper introduces a novel approach to address data collection and transmission challenges in IoT-enabled smart city frameworks. The proposed design integrates IoT-Cloud for efficient data collection and employs the energy efficient reliable data transmission (EERDT) model, optimizing IoT data transmission. The enhanced dragonfly routing algorithm, incorporating the firefly algorithm, enhances data routing efficiency. Experimental results demonstrate EERDT's superiority over energy-aware iot-routing (EAIR) and location-centric energy-harvesting aware-routing (LCEHAR), revealing significant improvements in communication overhead, data processing latency, and network lifetime. The EERDT exhibits substantial reductions in communication overhead, enhancing overall network performance. The EERDT model showcases lower data processing latency and energy consumption, highlighting its potential for resource-efficient IoT data transmission. This work contributes an innovative solution for smart city IoT networks, emphasizing performance enhancements and resource efficiency.

Diffractive deep neural networks: Theories, optimization, and applications

Optical neural networks (ONN) are experiencing a renaissance, driven by the transformative impact of artificial intelligence, as arithmetic pressures are progressively increasing the demand for optical computation. Diffractive deep neural networks (D2NN) are the important subclass of ONN, providing a novel architecture for computation with trained diffractive layers. Given that D2NN directly process light waves, they inherently parallelize multiple tasks and reduce data processing latency, positioning them as a promising technology for future optical computing applications. This paper begins with a brief review of the evolution of ONN and a concept of D2NN, followed by a detailed discussion of the theoretical foundations, model optimizations, and application scenarios of D2NN. Furthermore, by analyzing current application scenarios and technical limitations, this paper provides an evidence-based prediction of the future trajectory of D2NN and outlines a roadmap of research and development efforts to unlock its full potential.

Multi-Modal Trust Architecture for AI-HR Systems: Analyzing Technical Determinants of User Acceptance in Enterprise-Scale People Analytics Platforms

This comprehensive technical paper presents a novel multi-modal trust architecture for AI-driven HR systems, focusing on the critical aspects of user acceptance in enterprise-scale people analytics platforms. Through the implementation of advanced zero-knowledge proof protocols, explainable AI frameworks, blockchain-based audit trails, and federated learning approaches, the architecture achieved an 85% improvement in user confidence metrics. The system demonstrates remarkable performance across resistance prediction, technical integration, and trust analytics, processing over 9.5 million daily interactions with 99.999% reliability. Our implementation across 1,850 organizations showed an 82% enhancement in system trustworthiness and a 2.8x improvement in operational efficiency, while reducing algorithmic bias by 89%. The architecture's event-driven design and microservices implementation resulted in a 76% improvement in system responsiveness and a 92% reduction in data processing latency, establishing a new benchmark for trust-centric AI-HR systems.

Empowering Smart Cities with Fog Computing: A Versatile Framework for Enhanced Healthcare Services and Beyond

Fog Computing represents a distributed computing infrastructure strategically positioned at the network's edge, acting as an intermediate layer between remote cloud services and the data-generating smart devices on the ground. Leveraging this concept, a flexible and efficient smart city design emerges, offering a diverse range of applications, including smart healthcare, car parking, power management, water management, and waste management. The implementation of Fog computing enables reduced data processing latency and equitable workload distribution across fog nodes. The smart city system comprises several layers, namely connection, real-time processing, neighborhood linking, main processing, and data server layers. The flexibility of this framework allows for the scaling up or down of layers depending on specific smart city applications. In a case study focused on Smart healthcare services, the iFogSim platform was utilized to evaluate the system's performance. Notably, the results demonstrated a significant reduction in network usage, data processing latency, and processing costs when compared to traditional cloud computing solutions. Consequently, this improvement in efficiency translated into an enhanced user experience, offering superior scalability and reliability to users utilizing smart city services, including healthcare facilities.

Advancements in On-Device Deep Neural Networks

In recent years, rapid advancements in both hardware and software technologies have resulted in the ability to execute artificial intelligence (AI) algorithms on low-resource devices. The combination of high-speed, low-power electronic hardware and efficient AI algorithms is driving the emergence of on-device AI. Deep neural networks (DNNs) are highly effective AI algorithms used for identifying patterns in complex data. DNNs, however, contain many parameters and operations that make them computationally intensive to execute. Accordingly, DNNs are usually executed on high-resource backend processors. This causes an increase in data processing latency and energy expenditure. Therefore, modern strategies are being developed to facilitate the implementation of DNNs on devices with limited resources. This paper presents a detailed review of the current methods and structures that have been developed to deploy DNNs on devices with limited resources. Firstly, an overview of DNNs is presented. Next, the methods used to implement DNNs on resource-constrained devices are explained. Following this, the existing works reported in the literature on the execution of DNNs on low-resource devices are reviewed. The reviewed works are classified into three categories: software, hardware, and hardware/software co-design. Then, a discussion on the reviewed approaches is given, followed by a list of challenges and future prospects of on-device AI, together with its emerging applications.

A Fully Digital SRAM-Based Four-Layer In-Memory Computing Unit Achieving Multiplication Operations and Results Store

The separation of memory and arithmetic logic unit (ALU) in the von Neumann computing architecture hinders the development of big data and high-performance computing. In-memory computing (IMC) as a new computation method significantly reduces the latency and power consumption of data processing. In this study, we propose a fully digital static random access memory (SRAM)-based IMC architecture, which has the following advantages: 1) it simplifies multiplication to multicycle addition operations, reuses logic cells, and reduces hardware overhead; 2) by adding a pair of nMOS transistors to achieve internal write-back, the computational efficiency is improved, and at the same time, the final result of the multiplication can be stored locally, eliminating the need to read the computational result immediately; and 3) this scheme can be easily expanded to multiplication operations with different bit widths, which provides good scalability. A 4-kb SRAM-IMC macro chip is manufactured using the SMIC 55-nm technology to realize 4-bit multiplication, with an energy efficiency of 51.4 TOPS/W (0.9 V) and a throughput of 234.3 GOPS/mm <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$^{2}$</tex-math> </inline-formula> . The proposed multiplication–accumulation architecture is applied to a neural network, which achieves 98.7% accuracy with the Mixed National Institute of Standards and Technology database (MNIST) dataset.

Validation of High-Availability Model for Edge Devices and IIoT

Competitiveness in industry requires smooth, efficient, and high-quality operation. For some industrial applications or process control and monitoring applications, it is necessary to achieve high availability and reliability because, for example, the failure of availability in industrial production can have serious consequences for the operation and profitability of the company, as well as for the safety of employees and the surrounding environment. At present, many new technologies that use data obtained from various sensors for evaluation or decision-making require the minimization of data processing latency to meet the needs of real-time applications. Cloud/Fog and Edge computing technologies have been proposed to overcome latency issues and to increase computing power. However, industrial applications also require the high availability and reliability of devices and systems. The potential malfunction of Edge devices can cause a failure of applications, and the unavailability of Edge computing results can have a significant impact on manufacturing processes. Therefore, our article deals with the creation and validation of an enhanced Edge device model, which in contrast to the current solutions, is aimed not only at the integration of various sensors within manufacturing solutions, but also brings the required redundancy to enable the high availability of Edge devices. In the model, we use Edge computing, which performs the recording of sensed data from various types of sensors, synchronizes them, and makes them available for decision making by applications in the Cloud. We focus on creating a suitable Edge device model that works with the redundancy, by using either mirroring or duplexing via a secondary Edge device. This enables high Edge device availability and rapid system recovery in the event of a failure of the primary Edge device. The created model of high availability is based on the mirroring and duplexing of the Edge devices, which support two protocols: OPC UA and MQTT. The models were implemented in the Node-Red software, tested, and subsequently validated and compared to confirm the required recovery time and 100% redundancy of the Edge device. In the contrast to the currently available Edge solutions, our proposed extended model based on Edge mirroring is able to address most of the critical cases, where fast recovery is required, and no adjustments are needed for critical applications. The maturity level of Edge high availability can be further extended by applying Edge duplexing for process control.

Head-Mounted Miniature Motorized Camera and Laser Pointer Driven by Eye Movements

Recording a video scene as seen by an observer, materializing where is focused his visual attention and allowing an external person to point at a given object in this scene, could be beneficial for various applications such as medical education or remote training. Such a versatile device, although tested at the experimental laboratory demonstrator stage, has never been integrated in a compact and portable way in a real environment. In this context, we built a low-cost, light-weight, head-mounted device integrating a miniature camera and a laser pointer that can be remotely controlled or servo-controlled by an eye tracker. Two motorizations were implemented and tested (pan/tilt and Rilsey-prisms-based). The video was both recorded locally and transmitted wirelessly. Risley prisms allowed finer remote control of camera or laser pointer orientation (0.1° vs. 0.35°), but data processing and Wi-Fi transmission incur significant latency (~0.5 s) limiting the servo-controlling by eye movements. The laser beam was spatially shaped by a Diffractive Optical Element to facilitate object illumination or recognition. With this first proof-of-concept prototype, the data stream needs to be optimized to make full use of the eye tracker, but this versatile device can find various applications in education, healthcare or research.

Trainable quantization for Speedy Spiking Neural Networks.

Spiking neural networks are considered as the third generation of Artificial Neural Networks. SNNs perform computation using neurons and synapses that communicate using binary and asynchronous signals known as spikes. They have attracted significant research interest over the last years since their computing paradigm allows theoretically sparse and low-power operations. This hypothetical gain, used from the beginning of the neuromorphic research, was however limited by three main factors: the absence of an efficient learning rule competing with the one of classical deep learning, the lack of mature learning framework, and an important data processing latency finally generating energy overhead. While the first two limitations have recently been addressed in the literature, the major problem of latency is not solved yet. Indeed, information is not exchanged instantaneously between spiking neurons but gradually builds up over time as spikes are generated and propagated through the network. This paper focuses on quantization error, one of the main consequence of the SNN discrete representation of information. We argue that the quantization error is the main source of accuracy drop between ANN and SNN. In this article we propose an in-depth characterization of SNN quantization noise. We then propose a end-to-end direct learning approach based on a new trainable spiking neural model. This model allows adapting the threshold of neurons during training and implements efficient quantization strategies. This novel approach better explains the global behavior of SNNs and minimizes the quantization noise during training. The resulting SNN can be trained over a limited amount of timesteps, reducing latency, while beating state of the art accuracy and preserving high sparsity on the main datasets considered in the neuromorphic community.

Deep learning for enhancing internet of things: A comprehensive survey

The Internet of Things (IoT) has emerged as a transformative technology, connecting a wide range of devices and sensors to the internet, enabling data-driven decision-making and automation across various domains. Deep learning, a subset of machine learning, has played a pivotal role in advancing IoT applications by providing the means to process and interpret the massive volumes of data generated by IoT devices. This comprehensive survey provides an extensive review of the integration of deep learning techniques with IoT, aiming to offer a holistic understanding of the state-of-the-art research and practical implementations. The key motivations include handling complex IoT data and enabling smart applications across domains like healthcare, transportation, and industry 4.0. Real-world case studies demonstrate significant improvements on metrics like prediction accuracy, operational efficiency, and energy savings. The adoption of edge computing is further driven by the need to reduce latency in data processing and enhance real-time decisionmaking capabilities in these critical sectors. However, challenges remain around model interpretation, robustness, and computational complexity. Future IoT systems must focus on lightweight deep learning architectures tailored for edge devices, distributed and privacy-preserving analytics, and improved model transparency and fairness. Additionally, these future IoT systems should prioritize robust security measures to protect sensitive data and ensure the reliability and integrity of connected devices and networks. A systematic framework is proposed covering data curation, model development, deployment, and monitoring to guide adoption. The comprehensive nature of this survey aims to bridge the gap between theoretical knowledge and practical deployment, enabling a smoother integration of deep learning into IoT systems. By offering a structured overview of best practices and emerging trends, it empowers professionals to make informed decisions in their IoT projects.

Runtime reconfiguration of data services for dealing with out-of-range stream fluctuation in cloud-edge environments

The integration of cloud and IoT edge devices is of significance in reducing the latency of IoT stream data processing by moving services closer to the edge-end. In this connection, a key issue is to determine when and where services should be deployed. Common service deployment strategies used to be static based on the rules defined at the design time. However, dynamically changing IoT environments bring about unexpected situations such as out-of-range stream fluctuation, where the static service deployment solutions are not efficient. In this paper, we propose a dynamic service deployment mechanism based on the prediction of upcoming stream data. To effectively predict upcoming workloads, we combine the online machine learning methods with an online optimization algorithm for service deployment. A simulation-based evaluation demonstrates that, compared with those state-of-the art approaches, the approach proposed in this paper has a lower latency of stream processing.

Emotion Recognition by Facial Expression and Voice: Review and Analysis

Emotion is a scorching topic in the recent years due to the critical unseen stress incurred during the pandemic and post-pandemic. This is worsening with the recent economy’s inflation and increase of living cost, many employees are seriously affected and drawn forth many families saddened cases and tremendous drop of working performance. The increasing stress brings a lot of harm not only to the individual but to the company’s and country’s growth. To recognize emotion through a single model is less accurate, however, recruiting multiple-models may lead to latency in data processing and possibly misleading results if the input models data are not properly filtered and segmented. This paper will review, analyze and theoretically compare 15 facial expression methods and 17 voice methods of emotion recognition research works. It will outline the pros and cons of each method and discuss the accuracy of some of the standalone and hybrid emotion recognition methods. Some of the methods (such as CNN, KNN and SVM) can span over multiple-models, but reveal different level of strengths. This is very important to discover, so that one may replace or enhance the weaker level if applying the same method across the multiple-models. This paper will also illustrate different levels of popularity of the methods in each model for visual comparison in ease. Hopefully, it can cater the new researchers a quick identification on the most suitable method for recognizing the emotion through facial expression and/or voice.

Resource Orchestration of Cloud-Edge–based Smart Grid Fault Detection

Real-time smart grid monitoring is critical to enhancing resiliency and operational efficiency of power equipment. Cloud-based and edge-based fault detection systems integrating deep learning have been proposed recently to monitor the grid in real time. However, state-of-the-art cloud-based detection may require uploading a large amount of data and suffer from long network delay, while edge-based schemes do not adequately consider the detection requirement and thus cannot provide flexible and optimal performance. To solve these problems, we study a cloud-edge based hybrid smart grid fault detection system. Embedded devices are placed at the edge of the monitored equipment with several lightweight neural networks for fault detection. Considering limited communication resources, relatively low computation capabilities of edge devices, and different monitoring accuracies supported by these neural networks, we design an optimal communication and computational resource allocation method for this cloud-edge based smart grid fault detection system. Our method can maximize the processing throughput of the system and improve resource utilization while satisfying the data transmission and processing latency requirements. Extensive simulations are conducted and the results show the superiority of the proposed scheme over comparison schemes. We have also prototyped this system and verified its feasibility and performance in real-world scenarios.

Intelligent Sensing and Computing in Wireless Sensor Networks for Multiple Target Tracking

With sixth generation (6G) communication technologies, target sensing can be finished in milliseconds. The mobile tracking-oriented Internet of Things (MTT-IoT) as a kind of emerging application network can detect sensor nodes and track targets within their sensing ranges cooperatively. Nevertheless, huge data processing and low latency demands put tremendous pressure on the conventional architecture where sensing data is executed in the remote cloud and the short transmission distance of 6G channels presents new challenges into the design of network topology. To cope with the above difficulties, this paper proposes a new resource allocation scheme to perform delicate node scheduling and accurate tracking in multitarget tracking mobile networks. The dynamic tracking problem is formulated as an infinite horizon Markov Decision Process (MDP), where the state space that considers energy consumption, system responding delay, and target important degree is extended. A model-free reinforcement learning is applied to obtain satisfied tracking actions by frequent iterations, in which smart agents interact with the complicated environment directly. The performance of each episode is evaluated by the action-value function in search of the optimal reward. Simulation results demonstrate that the proposed scheme shows excellent tracking performance in terms of energy cost and tracking delay.

Design of DCO-OFDM System for VLC on Chip at the Register-Transfer Level

This paper reports a System-on-Chip (SoC) architecture design for the DC-biased optical OFDM (DCO-OFDM) Visible Light Communication (VLC) transceiver. The proposed SoC comprises several Digital Signal Processing (DSP) blocks, i.e., Fast Fourier Transform (FFT), Convolutional Encoder (CE), Viterbi Decoder, Quadrature Phase-Shift Keying (QPSK) Modulator/Demodulator, Interleaver/Deinterleaver, and Synchronizer. System was designed through the combination of two Intellectual Property (IP) types: designing IP from the scratch (custom-based IP) and employing available core accelerator IP served by the third party, which is Xilinx library (reuse-based IP). All DSP blocks were targeted for the FPGA development board (Xilinx Zynq SoC 7000), then combined with the ARM microprocessor. In this study, ARM microprocessors were used for various tasks, i.e., scheduling process, on-chip memory as a temporary data storage function, Analog-to-Digital Converter (A/D), Digital-to-Analog Converter (D/A), and Ethernet module as communication medium between SoCs and personal computer (PC). Testing was carried out on the Register Transfer Level (RTL) for hardware (H/W) and software (S/W) models implemented on ARM microprocessors. The system performances were measured through the point-to-point data communication scenarios between a PC transmitter and PC receiver. A 77 kbps of data communication speed and 2.9 ms of data processing latency were obtained using 100 MHz clock speed. The VLC on-chip was successfully demonstrated in RTL phase. This system is suitable for a low-rate communication system application, generally for joint VLC and Internet-things (IoT) technology, (then called as VLC/IoT).

Serverless data pipeline approaches for IoT data in fog and cloud computing

With the increasing number of Internet of Things (IoT) devices, massive amounts of raw data is being generated. The latency, cost, and other challenges in cloud-based IoT data processing have driven the adoption of Edge and Fog computing models, where some data processing tasks are moved closer to data sources. Properly dealing with the flow of such data requires building data pipelines, to control the complete life cycle of data streams from data acquisition at the data source, edge and fog processing, to Cloud side storage and analytics. Data analytics tasks need to be executed dynamically at different distances from the data sources and often on very heterogeneous hardware devices. This can be streamlined by the use of a Serverless (or FaaS) cloud computing model, where tasks are defined as virtual functions, which can be migrated from edge to cloud (and vice versa) and executed in an event-driven manner on data streams. In this work, we investigate the benefits of building Serverless data pipelines (SDP) for IoT data analytics and evaluate three different approaches for designing SDPs: (1) Off-the-shelf data flow tool (DFT) based, (2) Object storage service (OSS) based and (3) MQTT based. Further, we applied these strategies on three fog applications (Aeneas, PocketSphinx, and custom Video processing application) and evaluated the performance by comparing their processing time (computation time, network communication and disk access time), and resource utilization. Results show that DFT is unsuitable for compute-intensive applications such as video or image processing, whereas OSS is best suitable for this task. However, DFT is nicely fit for bandwidth-intensive applications due to the minimum use of network resources. On the other hand, MQTT-based SDP is observed with increase in CPU and Memory usage as the number of users rose, and experienced a drop in data units in the pipeline for PocketSphinx and custom video processing applications, however it performed well for Aeneas which had low size data units.