Base station load balancing system and method
The present disclosure provides a base station load balancing system including a communication network, a performance evaluator and an algorithm switching device. The communication network includes a base station and a plurality of user devices. The performance evaluator is connected to the communication network and evaluates a loading performance of the communication network in a time period according to a first loading data of the communication network in the time period. The algorithm switching device is connected to the performance evaluator and selects the algorithm used by the communication network as a selected algorithm according to the loading performance. The communication network, with the selected algorithm, allocates the connection relation between the base station and plurality of user devices according to the first loading data. The selected algorithm is a machine learning algorithm or a rule-based algorithm.
1 . A base station load balancing system, comprising:
a communication network, comprising a base station and a plurality of user devices;
a performance evaluator connected to the communication network, wherein the performance evaluator evaluates a loading performance of the communication network in a time period according to a first loading data of the communication network in the time period; and
an algorithm switching device connected to the performance evaluator, wherein the algorithm switching device selects an algorithm used by the communication network as a selected algorithm according to the loading performance;
wherein the communication network, with the selected algorithm, allocates a connection relation between the base station and plurality of user devices according to the first loading data, and the selected algorithm is a machine learning algorithm or a rule-based algorithm,
wherein the base station load balancing system further comprises:
a simulated network configured for generating a second loading data;
a database connected to the communication network and the simulated network, and configured for storing a storage data, wherein the storage data comprises the first loading data and the second loading data; and
a second access device connected to the database and configured for retrieving the second loading data,
wherein the base station load balancing system obtains the second loading data from the second access device and trains the machine learning algorithm according to the storage data.
2 . The base station load balancing system according to claim 1 , further comprising a first access device connected to the database, wherein the first access device is configured for retrieving the first loading data within a specific time interval.
3 . The base station load balancing system according to claim 2 , wherein the first access device provides the loading data within the specific time interval to the performance evaluator for evaluating the loading performance within the specific time interval, wherein when the loading performance within the specific time interval is less than a specific value, the algorithm used by the communication network is switched to the rule-based algorithm.
4 . The base station load balancing system according to claim 1 , wherein the base station load balancing system utilizes the first loading data to train the machine learning algorithm.
5 . The base station load balancing system according to claim 4 , wherein the first loading data is calculated as a handover parameter information through the rule-based algorithm, and the handover parameter information is labeled for the base station load balancing system to train the machine learning algorithm.
6 . The base station load balancing system according to claim 1 , wherein a model trained by the machine learning algorithm is recorded in a cloud backup system.
7 . The base station load balancing system according to claim 1 , wherein the communication network is formed by at least one of the radio access network (RAN) and the 5G core network.
8 . The base station load balancing system according to claim 1 , wherein the loading performance comprises at least one of the upload speed, the download speed and the throughput between the base station and the plurality of user devices.
9 . A base station load balancing method comprising steps of:
(a) providing a communication network comprising a base station and a plurality of user devices;
(b) evaluating a loading performance of the communication network in a time period according to a first loading data of the communication network in the time period by a performance evaluator; and
(c) selecting an algorithm used by the communication network as a selected algorithm according to the loading performance by an algorithm switching device,
wherein the communication network allocates a connection relation between the base station and plurality of user devices with the selected algorithm according to the first loading data, and the algorithm is a machine learning algorithm or a rule-based algorithm,
wherein the base station load balancing method further comprises steps of:
(d) generating a second loading data by a simulated network,
(e) storing the second loading data in a database;
(f) retrieving the second loading data of the database by a second access device; and
(e) training the machine learning algorithm according to the second loading data.
10 . The base station load balancing method according to claim 9 , further comprising steps of:
(h) storing the first loading data of the communication network in the database within a specific time interval;
(i) retrieving the first loading data of the database within the specific time interval by a first access device; and
(j) training the machine learning algorithm according to the first loading data within the specific time interval.
11 . The base station load balancing method according to claim 10 , wherein the first loading data is calculated as a handover parameter information through the rule-based algorithm, and the handover parameter information is labeled for the base station load balancing system to train the machine learning algorithm.
12 . The base station load balancing method according to claim 9 , wherein a model trained by the machine learning algorithm is recorded in a cloud backup system.
13 . The base station load balancing method according to claim 9 , wherein the communication network is formed by at least one of the radio access network (RAN) and the 5G core network.
14 . The base station load balancing method according to claim 9 , wherein the loading performance comprises at least one of the upload speed, the download speed and the throughput between the base station and the plurality of user devices.