Trade off analysis between fixed-time stabilization and energy consumption of nonlinear neural networks

2022 ◽  
Author(s):  
Yuchun Wang ◽  
Song Zhu ◽  
Hu Shao ◽  
Li Wang ◽  
Shiping Wen
Keyword(s):  
Neural Networks ◽  
Energy Consumption ◽  
Fixed Time ◽  
Trade Off ◽  
Nonlinear Neural Networks

scholarly journals Memristive Neural Networks: Zeolite‐Based Memristive Synapse with Ultralow Sub‐10‐fJ Energy Consumption for Neuromorphic Computation (Small 13/2021)

Small ◽  
2021 ◽  
Vol 17 (13) ◽  
pp. 2170057
Author(s):  
Tao Zeng ◽  
Xiaoqin Zou ◽  
Zhongqiang Wang ◽  
Guangli Yu ◽  
Zhi Yang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Energy Consumption ◽  
Memristive Neural Networks

scholarly journals Mobility-Included DNN Partition Offloading from Mobile Devices to Edge Clouds

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 229
Author(s):  
Xianzhong Tian ◽  
Juan Zhu ◽  
Ting Xu ◽  
Yanjun Li
Keyword(s):  
Neural Networks ◽  
Energy Consumption ◽  
Mobile Devices ◽  
Wireless Network ◽  
Deep Neural Networks ◽  
Mobile User ◽  
Computation Offloading ◽  
Long Latency ◽  
Total Latency ◽  
And Performance

The latest results in Deep Neural Networks (DNNs) have greatly improved the accuracy and performance of a variety of intelligent applications. However, running such computation-intensive DNN-based applications on resource-constrained mobile devices definitely leads to long latency and huge energy consumption. The traditional way is performing DNNs in the central cloud, but it requires significant amounts of data to be transferred to the cloud over the wireless network and also results in long latency. To solve this problem, offloading partial DNN computation to edge clouds has been proposed, to realize the collaborative execution between mobile devices and edge clouds. In addition, the mobility of mobile devices is easily to cause the computation offloading failure. In this paper, we develop a mobility-included DNN partition offloading algorithm (MDPO) to adapt to user’s mobility. The objective of MDPO is minimizing the total latency of completing a DNN job when the mobile user is moving. The MDPO algorithm is suitable for both DNNs with chain topology and graphic topology. We evaluate the performance of our proposed MDPO compared to local-only execution and edge-only execution, experiments show that MDPO significantly reduces the total latency and improves the performance of DNN, and MDPO can adjust well to different network conditions.

scholarly journals Traffic Light Priority for Trams in Warsaw as a Tool for Transport Policy and Reduction of Energy Consumption

2021 ◽  
Vol 13 (8) ◽  
pp. 4180
Author(s):  
Andrzej Czerepicki ◽  
Tomasz Krukowicz ◽  
Anna Górka ◽  
Jarosław Szustek
Keyword(s):  
Control System ◽  
Energy Consumption ◽  
Electric Energy ◽  
Fixed Time ◽  
Pollutant Emissions ◽  
Computer Simulation Model ◽  
Traffic Light ◽  
Electric Energy Consumption ◽  
Time Control ◽  
Reduction Of Energy Consumption

The article presents an analysis of priority solutions for trams at a selected sequence of intersections in Warsaw (Poland). An analysis of the literature has shown the topicality of this issue. A computer simulation model of a coordinated sequence of intersections was constructed. Three test scenarios were designed: the existing control system, the new coordinated fixed-time control system, and the adaptive control system with active priority. In the simulation process, detailed travel characteristics of trams and other traffic participants in a selected section were obtained for the three varying scenarios. Electric energy consumption for traction needs and pollutant emissions was then estimated for each of the variants. It was concluded that for the analyzed configuration, implementation of the adaptive priority will result in a reduction of tram time losses by up to 25%, a reduction in energy consumption by up to 23%, and a reduction in the emission of pollutants from individual vehicles by up to 3% in relation to the original variant. The conducted research may be the basis for a comprehensive method of assessing the effectiveness of applying the adaptative priority when designing new tramway lines and modernizing the existing ones.

Quasi fixed-time synchronization of memristive Cohen-Grossberg neural networks with reaction-diffusion

2020 ◽  
Vol 415 ◽  
pp. 74-83
Author(s):  
Fangmin Ren ◽  
Minghui Jiang ◽  
Hao Xu ◽  
Mengqin Li
Keyword(s):  
Neural Networks ◽  
Time Synchronization ◽  
Reaction Diffusion ◽  
Fixed Time

The multi-constrained least-cost multicast problem with neural networks in fixed time

2016 ◽  
Vol 10 ◽  
pp. 931-945
Author(s):  
N. Saber ◽  
M. Mestari ◽  
A. Ait El Mahjoub
Keyword(s):  
Neural Networks ◽  
Fixed Time
Sign in / Sign up

Export Citation Format

Share Document