Alleviating cell congestion in wireless networks
Systems and methods are provided for alleviating congestion of data traffic in a wireless network in a cell site. The methods determine congestion levels for respective data connections from mobile computing devices to a network through a cell tower in a cell site. The method further determines a congestion level associated with the cell site based on a weighted aggregate of varying congestion levels associated with the respective data connections in the cell site. The disclosed technology includes flow policies associated with congestion levels. The flow policies determine weights used for determining the weighted aggregate and maximum network bandwidth enforced for the respective data connections. The disclosed technology identifies data connections that consume abnormally high amount of network bandwidth and throttles with bias against data traffic associated with these data connections with heavy traffic. Through dynamically updating traffic shaping with bias, the present disclosure alleviates congestion in the cell site.
1. A computer-implemented method for causing reduction in data congestion at a cell site, the method comprising:
determining a first congestion level of a first data connection associated with a first computing device wirelessly connected to a cell site, wherein the first congestion level is based on a first data traffic flow of the first data connection, and the first congestion level corresponds to a first weight;
determining a second congestion level of a second data connection associated with a second computing device wirelessly connected to the cell site, wherein the second congestion level is based on a second data traffic flow of the second data connection, and the second congestion level corresponds to a second weight;
determining, based on aggregating a first number of data connections with the first congestion level, the first weight, a second number of data connections with the second congestion level, and the second weight, a cell congestion level of the cell site;
identifying, based on a combination including the cell congestion level and the first data traffic flow of the first data connection, the first data connection as having disproportionately high data traffic flow;
dynamically updating, based on the cell congestion level, a data traffic rule to enforce against the first data connection identified as having the disproportionately high data traffic flow; and
based on enforcing the updated data traffic rule, causing reduction in data congestion in the cell site.
2. The computer-implemented method of claim 1 , wherein the first congestion level includes one of:
a normal level,
a mild level, or
a severe level, and wherein a first maximum network throughput of the severe level is less than a second maximum network throughput of the normal level.
3. The computer-implemented method of claim 1 , wherein the first congestion level is based at least on a peak throughput, a time duration of the peak throughput, and an average throughput of data traffic in the first data connection.
4. The computer-implemented method of claim 1 , wherein the first congestion level and the second congestion level are distinct, and wherein a first maximum network throughput of the first data connection having the disproportionately high data traffic flow is less than a second maximum network bandwidth of the second data connection.
5. The computer-implemented method of claim 1 , wherein the cell site is wirelessly connected with one or more computing devices.
6. The computer-implemented method of claim 1 , wherein the cell site comprises one or more data connections.
7. The computer-implemented method of claim 1 , wherein the cell congestion level is based on a weighted sum of a number of data connections at each respective congestion level in the cell site.
8. The computer-implemented method of claim 1 , wherein the cell congestion level is based on a ratio between a weighted aggregate of data connections with distinct congestion levels ranging from a normal level to a severe level and a hypothetical weighted aggregate of all data connections being at the severe level.
9. A system for causing reduction in data congestion at a cell site, the system comprising:
at least one processor; and
memory storing instructions that, when executed by the at least one processor, cause the system to execute a method comprising:
determining a first congestion level of a first data connection of a first computing device wirelessly connected to a cell site, wherein the first congestion level is based on a first data traffic flow of the first data connection, and the first congestion level corresponds to a first weight;
determining a second congestion level of a second data connection of a second computing device wirelessly connected to the cell site, wherein the second congestion level is based on a second data traffic flow of the second data connection, and the second congestion level corresponds to a second weight;
determining, based on aggregating a first number of data connections with the first congestion level, the first weight, a second number of data connections with the second congestion level, and the second weight, a cell congestion level of the cell site;
identifying, based on a combination including the cell congestion level and the first data traffic flow of the first data connection, the first data connection as having disproportionately high data traffic flow;
dynamically updating, based on the cell congestion level, a data traffic rule to enforce against the first data connection identified as having the disproportionately high data traffic flow; and
based on enforcing the updated data traffic rule, causing reduction in data congestion in the cell site.
10. The system of claim 9 , wherein the first congestion level includes one of:
a normal level,
a mild level, or
a severe level, and wherein a first maximum network throughput of the severe level is less than a second maximum network throughput of the normal level.
11. The system of claim 9 , wherein the first congestion level is based at least on a peak throughput, a time duration of the peak throughput, and an average throughput of data traffic in the first data connection.
12. The system of claim 9 , wherein the first congestion level and the second congestion level are distinct, and wherein a first maximum network throughput of the first data connection having the disproportionately high data traffic flow is less than a second maximum network bandwidth of the second data connection.
13. The system of claim 9 , wherein the cell site is wirelessly connected with one or more computing devices.
14. The system of claim 9 , wherein the cell site comprises one or more data connections.
15. The system of claim 9 , wherein the cell congestion level is based on a weighted sum of a number of data connections at each respective congestion level in the cell site.
16. The system of claim 9 , wherein the cell congestion level is based on a ratio between a weighted aggregate of data connections with distinct congestion levels ranging from a normal level to a severe level and a hypothetical weighted aggregate of all data connections being at the severe level.
17. A method for alleviating data congestion at a cell site, the method comprising:
determining, based on aggregating a number of data connections and first and second weights corresponding to respective congestion levels of respective first and second data connections in a cell site, a cell congestion level of the cell site, wherein the respective congestion levels are based on first and second data traffic flow of the respective first and second data connections;
identifying, based on the cell congestion level, a flow policy of the cell site, wherein the flow policy includes a data traffic rule enforced upon at least in part of the respective first and second data connections in the cell site, and wherein the data traffic rule comprises enforcing a maximum throughput to data traffic;
enforcing the flow policy upon one or more data connections of the respective first and second data connections in the cell site;
dynamically updating, based on the cell congestion level, the flow policy of the cell site; and
causing reduction in data congestion at the cell site.
18. The method of claim 17 , wherein the cell congestion level includes one of:
a normal level,
a mild level, or
a severe level.
19. The method of claim 18 , the method further comprising:
when the cell congestion level of the cell site includes the severe level, identify a set of data connections including a data connection with a congestion level of at least a severe level; and
enforce the flow policy of the cell site, wherein the flow policy of the cell site includes enforcing a predetermined maximum throughput to data traffic of each of the set of data connections.
20. The method of claim 19 , the method further comprising:
creating a new data connection in the cell site;
enforcing a first maximum throughput upon data traffic of the new data connection; and
enforcing, upon the dynamically updating the flow policy of the cell site, the predetermined maximum throughput upon data traffic of the new data connection, wherein the predetermined maximum throughput is less than the first maximum throughput.