Commissariat &#xc0; L'&#xc9;nergie Atomique Et Aux &#xc9;nergies Alternatives

Mohamed Sana

Emilio Calvanese Strinati

Benoît Miscopein

Antonio De Domenico

François Dehmas

Sébastien De Rivaz

Nicola Di Pietro

Florian Wolf

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

The present invention relates to a method for estimating a distance between nodes of an LPWA network. First and second nodes, respectively, successively transmit a narrow band signal at a plurality of carrier frequencies to each other. The second and first nodes, respectively, receive the transmitted signals and demodulate them into baseband signals. Complex values representative of a forward-backward function of the transmission channel between two nodes are obtained from the baseband demodulated signals. These complex values are then provided to a previously supervisingly trained neural network, the neural network giving an estimation of the distance separating the first node and the second node. The present invention also relates to a method for estimating the position of a node in an LPWA network using the above-noted distance estimation method.

Distance estimation method in an LPWA network and a position estimation method associated therewith

A method for associating user equipment with base stations of a cellular network such as a 5G network. An agent receives an observation of its environment and deduces an action therefrom, this action being manifested as an association request of the user to a neighboring base station. This action is chosen according to a strategy of the user seeking the maximum of a function of action value for the observation and several possible actions. Once the actions have been carried out by the various actions, a common reward is provided by the network to the various users, the latter being zero in the case of a collision of association requests and the result of a utility function otherwise. The function of action value for the various possible actions is predicted by a recurrent neural network trained on a set of experiments stored in a local memory.

Method for associating user equipment in a cellular network via multi-agent reinforcement learning

Growing community of inventors

Grenoble, France

Mohamed Sana