COME-UP: Computation Offloading in Mobile Edge Computing with LSTM Based User Direction Prediction

Zaman, Sardar Khaliq uz; Jehangiri, Ali Imran; Maqsood, Tahir; Umar, Arif Iqbal; Khan, Muhammad Amir; Jhanjhi, N. Z.; Shorfuzzaman, Mohammad; Masud, Mehedi

doi:10.3390/app12073312

Cited by 28 publications

(16 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, in MEC, the unknown location, speed and direction of the user on the mobile device will affect the EC-IoT architecture application system latency. Zaman et al [50] proposed a framework termed COME-UP Computation Offloading in mobile edge computing with Long-Short Term Memory (LSTM) based user direction prediction. The framework effectively reduces delays and energy consumption and improves resource efficiency.…”

Section: Task Offloadingmentioning

confidence: 99%

Application and Research of IoT Architecture for End-Net-Cloud Edge Computing

Zhang

Zhou

et al. 2022

Electronics

View full text Add to dashboard Cite

At the edge of the network close to the source of the data, edge computing deploys computing, storage and other capabilities to provide intelligent services in close proximity and offers low bandwidth consumption, low latency and high security. It satisfies the requirements of transmission bandwidth, real-time and security for Internet of Things (IoT) application scenarios. Based on the IoT architecture, an IoT edge computing (EC-IoT) reference architecture is proposed, which contained three layers: The end edge, the network edge and the cloud edge. Furthermore, the key technologies of the application of artificial intelligence (AI) technology in the EC-IoT reference architecture is analyzed. Platforms for different EC-IoT reference architecture edge locations are classified by comparing IoT edge computing platforms. On the basis of EC-IoT reference architecture, an industrial Internet of Things (IIoT) edge computing solution, an Internet of Vehicles (IoV) edge computing architecture and a reference architecture of the IoT edge gateway-based smart home are proposed. Finally, the trends and challenges of EC-IoT are examined, and the EC-IoT architecture will have very promising applications.

show abstract

Section: Task Offloadingmentioning

confidence: 99%

Application and Research of IoT Architecture for End-Net-Cloud Edge Computing

Zhang

Zhou

et al. 2022

Electronics

View full text Add to dashboard Cite

show abstract

“…In the field of computer vision, LSTM is primarily used for video classification, image annotation, video annotation [11], and recently popular visual Q&A. In the field of engineering practice, computation offloading in mobile edge computing can also be predicted by LSTM [12].…”

Section: Related Workmentioning

confidence: 99%

Sequential Characteristics Based Operators Disassembly Quantization Method for LSTM Layers

Wang

Yang

2022

Applied Sciences

View full text Add to dashboard Cite

Embedded computing platforms such as neural network accelerators deploying neural network models need to quantize the values into low-bit integers through quantization operations. However, most current embedded computing platforms with a fixed-point architecture do not directly support performing the quantization operation for the LSTM layer. Meanwhile, the influence of sequential input data for LSTM has not been taken into account by quantization algorithms. Aiming at these two technical bottlenecks, a new sequential-characteristics-based operators disassembly quantization method for LSTM layers is proposed. Specifically, the calculation process of the LSTM layer is split into multiple regular layers supported by the neural network accelerator. The quantization-parameter-generation process is designed as a sequential-characteristics-based combination strategy for sequential and diverse image groups. Therefore, LSTM is converted into multiple mature operators for single-layer quantization and deployed on the neural network accelerator. Comparison experiments with the state of the art show that the proposed quantization method has comparable or even better performance than the full-precision baseline in the field of character-/word-level language prediction and image classification applications. The proposed method has strong application potential in the subsequent addition of novel operators for future neural network accelerators.

show abstract

“…[ 16 , 17 ] jointly considered the task partition and resource allocation issues to not only balance the overload of each server but also exploit the computational capability of each server more efficiently. Recently, deep learning techniques were extensively employed to optimize the computation offloading problem [ 18 , 19 , 20 , 21 , 22 ]. Ref.…”

Section: Introductionmentioning

confidence: 99%

“…Ref. [ 22 ] exploited the LSTM network to further improve the system performance by considering each UE’s direction.…”

Section: Introductionmentioning

confidence: 99%

JUTAR: Joint User-Association, Task-Partition, and Resource-Allocation Algorithm for MEC Networks

Liu

Wang

et al. 2023

Sensors

View full text Add to dashboard Cite

Mobile edge computing (MEC) is a promising technique to support the emerging delay-sensitive and compute-intensive applications for user equipment (UE) by means of computation offloading. However, designing a computation offloading algorithm for the MEC network to meet the restrictive requirements towards system latency and energy consumption remains challenging. In this paper, we propose a joint user-association, task-partition, and resource-allocation (JUTAR) algorithm to solve the computation offloading problem. In particular, we first build an optimization function for the computation offloading problem. Then, we utilize the user association and smooth approximation to simplify the objective function. Finally, we employ the particle swarm algorithm (PSA) to find the optimal solution. The proposed JUTAR algorithm achieves a better system performance compared with the state-of-the-art (SOA) computation offloading algorithm due to the joint optimization of the user association, task partition, and resource allocation for computation offloading. Numerical results show that, compared with the SOA algorithm, the proposed JUTAR achieves about 21% system performance gain in the MEC network with 100 pieces of UE.

show abstract

COME-UP: Computation Offloading in Mobile Edge Computing with LSTM Based User Direction Prediction

Cited by 28 publications

References 51 publications

Application and Research of IoT Architecture for End-Net-Cloud Edge Computing

Application and Research of IoT Architecture for End-Net-Cloud Edge Computing

Sequential Characteristics Based Operators Disassembly Quantization Method for LSTM Layers

JUTAR: Joint User-Association, Task-Partition, and Resource-Allocation Algorithm for MEC Networks

Contact Info

Product

Resources

About