The Intelligent Routing Control Strategy Based on Deep Learning

2021 ◽  
pp. 585-598
Author(s):  
Jinsuo Jia ◽  
Yichun Fu ◽  
Guiyu Zhang ◽  
Xiaochen Liang ◽  
Peng Xu
Keyword(s):  
Deep Learning ◽  
Control Strategy ◽  
Intelligent Routing ◽  
Routing Control

scholarly journals Intelligent Routing Control for MANET Based on Reinforcement Learning

2018 ◽  
Vol 232 ◽  
pp. 04002
Author(s):  
Fang Dong ◽  
Ou Li ◽  
Min Tong
Keyword(s):  
Reinforcement Learning ◽  
Control Algorithm ◽  
Rapid Development ◽  
Selection Strategy ◽  
Performance Simulation ◽  
Multiple Parameters ◽  
Intelligent Routing ◽  
Routing Control ◽  
The Cost

With the rapid development and wide use of MANET, the quality of service for various businesses is much higher than before. Aiming at the adaptive routing control with multiple parameters for universal scenes, we propose an intelligent routing control algorithm for MANET based on reinforcement learning, which can constantly optimize the node selection strategy through the interaction with the environment and converge to the optimal transmission paths gradually. There is no need to update the network state frequently, which can save the cost of routing maintenance while improving the transmission performance. Simulation results show that, compared with other algorithms, the proposed approach can choose appropriate paths under constraint conditions, and can obtain better optimization objective.

scholarly journals Energy Routing Control Strategy for Integrated Microgrids Including Photovoltaic, Battery-Energy Storage and Electric Vehicles

Energies ◽  
2019 ◽  
Vol 12 (2) ◽  
pp. 302 ◽  
Author(s):  
Yingpei Liu ◽  
Yan Li ◽  
Haiping Liang ◽  
Jia He ◽  
Hanyang Cui
Keyword(s):  
Energy Storage ◽  
Electric Vehicles ◽  
Control Strategy ◽  
Reactive Power ◽  
Constant Current ◽  
Battery Energy Storage ◽  
Energy Internet ◽  
Dc Voltage ◽  
Routing Control ◽  
Battery Energy

The Energy Internet is an inevitable trend of the development of electric power system in the future. With the development of microgrids and distributed generation (DG), the structure and operation mode of power systems are gradually changing. Energy routers are considered as key technology equipment for the development of the Energy Internet. This paper mainly studies the control of the LAN-level energy router, and discusses the structure and components of the energy router. For better control of the power transmission of an energy router, the energy routing control strategy for an integrated microgrid, including photovoltaic (PV) energy, battery-energy storage and electric vehicles (EVs) is studied. The front stage DC/DC converter of the PV system uses maximum power point tracking (MPPT) control. The constant current control is used by the bidirectional DC/DC converter of the battery-energy storage system and the EV system when they discharge. The DC/AC inverters adopt constant reactive power and constant DC voltage control. Constant current constant voltage control is adopted when an EV is charged. The control strategy model is simulated by Simulink, and the simulation results verify the feasibility and effectiveness of the proposed control strategy. The DG could generate reactive power according to the system instructions and ensure the stable output of the DC voltage of the energy router.

Predictive Feedback Routing Control Strategy for Freeway Network Traffic

2003 ◽  
Vol 1856 (1) ◽  
pp. 62-73 ◽  
Author(s):  
Yibing Wang ◽  
Markos Papageorgiou ◽  
Albert Messmer
Keyword(s):  
Control Strategy ◽  
User Equilibrium ◽  
Time Step ◽  
Equilibrium Conditions ◽  
Traffic Conditions ◽  
New Strategy ◽  
Feedback Strategies ◽  
Routing Control ◽  
Freeway Networks ◽  
The One

Available routing strategies for freeway networks may be classified as feedback and iterative strategies. Feedback strategies base their routing decisions on real-time measurable or estimable information only, via employment of simple regulators, while iterative strategies run a freeway network model repeatedly to achieve exact user equilibrium conditions over a future time horizon. A predictive feedback routing control strategy was developed with the aim of incorporating the advantages of both classes of strategies on the one hand and attenuating their disadvantages on the other hand. The new strategy runs a mathematical model only once at each time step and bases its routing decisions on the predicted instead of the currently prevailing traffic conditions. The investigations indicate that satisfactory routing results are achieved by use of this strategy. The corresponding performance evaluation was conducted in detail by comparison with the feedback and iterative strategies.

Sign in / Sign up

Export Citation Format

Share Document