Method for optimizing traffic between autonomous systems
A method of distributing traffic across a set of links interconnecting a local autonomous system with autonomous systems neighboring the local autonomous system is disclosed. The method comprises /a/ receiving information relating to characteristics of the neighboring autonomous systems; /b/ determining a result of a reward function, representative of a state of the set of links; /c/ triggering, based on the information received and the result of the reward function, at least one action influencing a distribution of traffic across the set of links so as to optimize the load state of the set of links; /d/ reiterating steps /a/ to /c/; the at least one action being identified by an artificial intelligence configured to learn to identify, on the basis of successive results of the reward function, actions enabling traffic to be distributed across the set of links to optimize the load state of the set of links.
1. A method for distributing traffic across a set of links interconnecting a local autonomous system with a plurality of autonomous systems neighboring the local autonomous system, the method comprising:
/a/ receiving information at least relating to characteristics of the plurality of neighboring autonomous systems;
/b/ determining, from the information received, a result of a reward function, representative of a state of the set of links;
/c/ triggering, based on the information received and the result of the reward function, at least one action influencing a distribution of traffic across the set of links so as to optimize the load state of the set of links;
/d/ reiterating steps /a/ to /c/;
the at least one action being identified by an artificial intelligence configured to learn to identify, on the basis of successive results of the reward function, actions enabling traffic to be distributed across the set of links so as to optimize the load state of the set of links,
wherein the information received according to step /a/ is representative of:
a load state of the set of links;
a type of autonomous system for each of the neighboring autonomous systems; and
prefixes relating to networks hosted by the local autonomous system and the neighboring autonomous systems, the prefixes being announced by an autonomous system to its neighbors,
wherein the at least one action triggered according to step /c/ comprises the modification of the at least one Border Gateway Protocol (BGP) attribute, and
wherein the modification of the at least one BGP attribute takes into consideration a propagation delay of the prefixes to be announced.
2. The method according to claim 1 , wherein the artificial intelligence comprises a neural network.
3. The method according to claim 1 , wherein optimization of the load state according to step /c/ comprises the convergence of the load state towards a desired load state.
4. The method according to claim 1 , wherein the type of autonomous system is a client autonomous system, a peer autonomous system or a provider autonomous system.
5. The method according to claim 1 , wherein the modification of the at least one BGP attribute comprises the modification of at least one BGP attribute among: multi exit discriminator (MED), autonomous system (AS) PATH, PREFIX.
6. The method according to claim 1 , wherein the method comprises a step of triggering at least one action randomly influencing a distribution of traffic across at least part of the set of links.
7. A decision-making device for distributing traffic across a set of links interconnecting a local autonomous system with a plurality of autonomous systems neighboring the local autonomous system, the device comprising:
at least one interface configured to:
/a/ receive information at least relating to characteristics of the plurality of neighboring autonomous systems;
at least one processing circuit configured to:
/b/ determine, from the information received, a result of a reward function, representative of a state of the set of links;
/c/ trigger, based on the information received and the result of the reward function, at least one action influencing a distribution of traffic across the set of links so as to optimize the load state of the set of links; and
/d/ reiterate steps /a/ to /c/;
the device comprising an artificial intelligence configured to learn to identify, on the basis of successive results of the reward function, the at least one action enabling traffic to be distributed across the set of links so as to optimize the load state of the set of links, wherein the information received according to /a/ is representative of:
a load state of the set of links;
a type of autonomous system for each of the neighboring autononmous systems; and
wherein the at least one action triggered according to /c/ comprises the modification of at least one Border Gateway Protocol (BGP) attribute, and
wherein the modification of the at least one BGP attribute takes into consideration a propagation delay of the prefixes to be announced.
8. A processing circuit comprising a processor and a memory, the memory storing program code instructions of a computer program which, when these instructions are executed by the processor, implement the method according to claim 1 .