Task Placement Across Multiple Public Clouds With Deadline Constraints for Smart Factory

Li, Boyu; Zhao, Zhipeng; Guan, Yan; Ai, Ning; Dong, Xiaowen; Wu, Bin

doi:10.1109/access.2017.2779462

Cited by 12 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Details about the customer’s machine are saved in a cloud and he can investigate all the system details especially faults. This cloud solution is vulnerable to hackers, Lenze, along with another company, have provided a secure solution that is acceptable for today’s industry [30].…”

Section: Evolution and Enablers Of Industrial Internet Of Thingsmentioning

confidence: 99%

See 1 more Smart Citation

Fog Computing Enabling Industrial Internet of Things: State-of-the-Art and Research Challenges

Basir¹,

Qaisar²,

Ali

et al. 2019

Sensors

103

View full text Add to dashboard Cite

Industry is going through a transformation phase, enabling automation and data exchange in manufacturing technologies and processes, and this transformation is called Industry 4.0. Industrial Internet-of-Things (IIoT) applications require real-time processing, near-by storage, ultra-low latency, reliability and high data rate, all of which can be satisfied by fog computing architecture. With smart devices expected to grow exponentially, the need for an optimized fog computing architecture and protocols is crucial. Therein, efficient, intelligent and decentralized solutions are required to ensure real-time connectivity, reliability and green communication. In this paper, we provide a comprehensive review of methods and techniques in fog computing. Our focus is on fog infrastructure and protocols in the context of IIoT applications. This article has two main research areas: In the first half, we discuss the history of industrial revolution, application areas of IIoT followed by key enabling technologies that act as building blocks for industrial transformation. In the second half, we focus on fog computing, providing solutions to critical challenges and as an enabler for IIoT application domains. Finally, open research challenges are discussed to enlighten fog computing aspects in different fields and technologies.

show abstract

Section: Evolution and Enablers Of Industrial Internet Of Thingsmentioning

confidence: 99%

“…The intelligent production process comprises smart starting and ending of manufacturing processes. Vertical and horizontal integration means all the steps during the smart/intelligent production process are integrated throughout the life cycle i.e., from starting phase to ending phase [30].…”

Section: Evolution and Enablers Of Industrial Internet Of Thingsmentioning

confidence: 99%

Fog Computing Enabling Industrial Internet of Things: State-of-the-Art and Research Challenges

Basir¹,

Qaisar²,

Ali

et al. 2019

Sensors

103

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning has achieved significant successful processing tasks in various natural languages, such as semantic analysis [1], machine translation [2], text abstract [3] and other intelligent domains, such as automatic speech recognition [4,5], intelligent fault diagnosis [6][7][8][9] and smart factory [10][11][12]. It has also achieved good performance in answer selection [13][14][15][16].…”

Section: Introductionmentioning

confidence: 99%

Double attention recurrent convolution neural network for answer selection

et al. 2020

View full text Add to dashboard Cite

Answer selection is one of the key steps in many question answering (QA) applications. In this paper, a new deep model with two kinds of attention is proposed for answer selection: the double attention recurrent convolution neural network (DARCNN). Double attention means self-attention and cross-attention. The design inspiration of this model came from the transformer in the domain of machine translation. Self-attention can directly calculate dependencies between words regardless of the distance. However, self-attention ignores the distinction between its surrounding words and other words. Thus, we design a decay self-attention that prioritizes local words in a sentence. In addition, cross-attention is established to achieve interaction between question and candidate answer. With the outputs of self-attention and decay self-attention, we can get two kinds of interactive information via cross-attention. Finally, using the feature vectors of the question and answer, elementwise multiplication is used to combine with them and multilayer perceptron is used to predict the matching score. Experimental results on four QA datasets containing Chinese and English show that DARCNN performs better than other answer selection models, thereby demonstrating the effectiveness of self-attention, decay self-attention and cross-attention in answer selection tasks.

show abstract

“…Some of these require immediate processing of data generated by an edge device to extract meaningful information. Previously, data obtained from an edge device was sent to the server and processed using a prelearned AI network [5]. However, a delay existed in the communication between the device and the server.…”

Section: Introductionmentioning

confidence: 99%

Area- and Energy-Efficient STDP Learning Algorithm for Spiking Neural Network SoC

Kim

Choi

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Recently, spiking neural networks have gained attention owing to their energy efficiency. Allto-all spike-time dependent plasticity is a popular learning algorithm for spiking neural networks because it is suitable for nondifferentiable spike event-based learning and requires fewer computations than backpropagation-based algorithms. However, the hardware implementation of all-to-all spike-time dependent plasticity is limited by the large storage area required for spike history and large energy consumption caused by frequent memory access. We propose a time-step scaled spike-time dependent plasticity to reduce the storage area required for spike history by reducing the area of the spike-time dependent plasticity learning circuit by 60% and a post-neuron spike-referred spike-time dependent plasticity to reduce the energy consumption by 99.1% by efficiently accessing the memory while learning. The accuracy of Modified National Institute of Standards and Technology image classification degraded by less than 2% when both time-step scaled spike-time dependent plasticity and post-neuron spike-referred spike-time dependent plasticity were applied. Thus, the proposed hardware-friendly spike-time dependent plasticity algorithms make all-to-all spike-time dependent plasticity implementable in more compact areas while reducing energy consumption and experiencing insignificant accuracy degradation. INDEX TERMS Spike-time dependent plasticity (STDP), Time-step scaled STDP (TS-STDP), Postneuron spike-referred STDP (PR-STDP), Spiking neural network (SNN) Wij Learning neuron Synaptic weight Off-chip On-chip Pre-neuron spike Post-neuron spike ... ... FIGURE 1. Concept of SNN and its structure.

show abstract

Task Placement Across Multiple Public Clouds With Deadline Constraints for Smart Factory

Cited by 12 publications

References 18 publications

Fog Computing Enabling Industrial Internet of Things: State-of-the-Art and Research Challenges

Fog Computing Enabling Industrial Internet of Things: State-of-the-Art and Research Challenges

Double attention recurrent convolution neural network for answer selection

Area- and Energy-Efficient STDP Learning Algorithm for Spiking Neural Network SoC

Contact Info

Product

Resources

About