Determination method and determination system of route transmitting paths in internet-of-things environment
A transmission path and determination method technology, applied in the field of determination method and determination system of routing transmission path, can solve problems such as incomplete routing parameter information
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 2
[0066] image 3 It is a structural block diagram of the determination system provided by Embodiment 2 of the present invention. Such as image 3 As shown, a system for determining a routing transmission path in an Internet of Things environment, the system for determining includes:
[0067] Decision model building module 21 is used to set up a Markov routing decision model according to the current state of the routing node and the currently selected action;
[0068] A value function determination module 22, configured to determine the value function of each routing transmission path according to the Markov routing decision model;
[0069] The optimal path determination module 23 is used to determine the optimal transmission path of the route according to the value function of each of the route transmission paths, utilizing the Bellman optimality theorem equation (dynamic programming equation);
[0070] The model update module 24 is used to update the Markov routing decision...
Embodiment 3
[0073] This embodiment aims at the routing selection technology in the uncertain environment of the Internet of Things, analyzes the necessary conditions for routing selection, and proposes a method for routing selection in the unknown environment of the Internet of Things based on reinforcement learning weighted balance, so as to realize the routing in unknown or incomplete routing conditions. In this case, determine the optimal transmission path.
[0074] Figure 4 A schematic diagram of reinforcement learning weighted equalization unknown environment routing provided by Embodiment 3 of the present invention. Such as Figure 4 As shown, in this embodiment, when constructing routes in an unknown environment, reinforcement learning is used to construct a Markov routing decision model including node state sets, forwarding action sets, state transition probabilities, and reward value quadruples, and Bellman optimality theorem The equation (BellmanEquation, dynamic programming ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


