Method for controlling, optimizing and selecting of heterogeneous network access based on Q-learning
A heterogeneous network, optimization selection technology, applied in the field of wireless networks, can solve the problems of complex calculation, network type cannot achieve global optimization, and it is difficult to apply to actual systems.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0082] Specific implementation mode one: the following combination Figure 1 to Figure 3 Describe this embodiment, the Q-learning-based heterogeneous network access control optimization selection method described in this embodiment, the method includes the following steps:
[0083] Step 1. Judging the state of the heterogeneous network when a new user is connected;
[0084] Step 2: Query the Q value table, and select the subnetwork corresponding to the largest Q value in the Q value table corresponding to the heterogeneous network state in step 1 as the access network of the new user.
[0085] The heterogeneous network refers to a converged heterogeneous network composed of a WCDMA subnet and a WLAN subnet in a loosely coupled manner,
[0086] The heterogeneous network state is jointly determined according to four network states based on interference of the WCDMA subnetwork and four network states based on channel busy rate of the WLAN subnetwork,
[0087] Four kinds of netw...
specific Embodiment approach 2
[0174] Specific implementation mode two: this implementation mode will further illustrate implementation mode one, I 1 = 4, I 2 = 8, I 3 =12.
specific Embodiment approach 3
[0175] Embodiment 3: This embodiment further describes Embodiment 1, and the discount factor γ=0.9.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 