User experience is the ultimate quality of service criterion for modern WLAN networks. However, network configuration approaches are mainly network-centric. We envision a paradigm shift, empowering users in network management. We study how automated negotiation and collective intelligence can support the democratic configuration of a wireless network, leveraging client and provider interests. This new paradigm allows for flexible network configuration, which enables better exploitation of resources considering the clients real usage and needs, and a fair distribution of throughput among users.

Channel allocation in dense, decentralized Wi-Fi networks is a challenging due to the highly nonlinear solution space and the difficulty to estimate the opponent’s utility model. So far, only centralized or mediated approaches have succeeded in applying negotiation to this setting. We propose the first two fully-distributed negotiation approaches for Wi-Fi channel assignment. Both of them leverage a pre-sampling of the utility space with simulated annealing and a noisy estimation of the Wi-Fi utility function. Regarding negotiation protocols, one of the approaches makes use of the Alternating Offers protocol, while the other uses the novel Multiple Offers Protocol for Multilateral Negotiations with Partial Consensus (MOPaC), which naturally matches the problem peculiarities. We compare the performance of our proposed approaches with the previous mediated approach, based on simple text mediation. Our experiments show that our approaches yield better utility outcomes, better fairness and less information disclosure than the mediated approach.

Channel allocation in dense Wi-Fi networks is a complex problem due to its nonlinear and exponentially sized solution space. Negotiating over this domain is a challenge, since it is difficult to estimate opponent’s utility. Based on our previous work in mediated techniques, we propose the first two fully-distributed multi-agent negotiations for Wi-Fi channel assignment. Both of them use a simulated annealing sampling process and a noisy model graph estimation. One is designed for Alternating Offers protocols, while the other uses the novel Multiple Offers Protocol for Multilateral Negotiations with Partial Consensus (MOPaC), with experimental promising features for our particular domain. Our experiments compare both proposals against their mediated counterparts, showing similar results on social welfare, Nash product and fairness, but improving privacy and communication overhead.