Commissariat a L'energie Atomique Et Aux Energies Alternatives

Nicola Di Pietro

Emilio Calvanese Strinati

Benoît Miscopein

Mohamed Sana

A method for associating user equipment with base stations of a cellular network, in particular of a heterogeneous network such as a 5G network, uses a multi-agent reinforcement learning (MARL) algorithm. When a user equipment enters the network, the agent associated with this equipment downloads the instance of an association meta model to a coordinating unit, pre-trained by means of reinforcement learning. The agent subsequently constructs a local observation vector, comprising observables relating to the user equipment, and a global observation vector, including observables relating to the environment of this equipment. The local and global observation vectors are projected into the same reference space, the concatenation of the vectors thus projected encoding the state of the agent. It deduces from the model and from this state, an association decision. The model is updated according to a policy gradient method to consider evolution of the environment of the user.

Method of association of user equipment in a cellular network according to a transferable association policy

A method for a mobile terminal to access a network with a multi-link with a plurality of network access points. When the terminal wishes to obtain a quality of service expressed in the form of a minimum bitrate constraint on the uplink, it determines the identity and the number of access points with which it must establish a link to meet this constraint while minimizing its emission power. A MEC network with a mobile terminal that can request the network to support a computational task under latency constraint.

Growing community of inventors

Grenoble, France

Nicola Di Pietro