One-to-Many Negotiation QoE Management Mechanism for End-User Satisfaction

Abstract

Quality of Experience (QoE) is defined as the measure of end-user satisfaction with the service. Existing works addressing QoE-management rely on a binary vision of end-user satisfaction. This vision has been criticized by the growing empirical evidence showing that QoE is rather a degree. This article aims to go beyond the binary vision and propose a QoE management mechanism. We propose a one-to-many negotiation mechanism allowing the provider to undertake satisfaction management: to meet fine-grained user QoE goals, while still minimizing the costs. This problem is formulated as an optimization problem, for which a linear model is proposed. For reference, a generic linear program solver is used to find the optimal solution, and an alternative heuristic algorithm is devised to improve the responsiveness when the system has to scale up with a fast growing number of users. Both are implemented and experimentally evaluated against state-of-the-art one-to-many negotiation frameworks.

Autonomous Bidding & Coordinated Acceptance in One-to-Many Negotiations

“…However, their focus was on the agent's overall architecture and the identification of few coordination heuristics. The same holds true for follow up works that used Rahwan's agent design in a single-deal setting [8], [9], or a multi-deal one [10], and for works that proposed agents the coordination and negotiation strategies of which are not decoupled [11], [12]. Moreover, there is no previous work that proposes some coordination strategy that uses outcome estimations in its decision-making.…”

“…Mansour & Kowalczyk [14], in a context where multiple, non-overlapping deals over single-issue items can be reached, proposed three coordination strategies (or metastrategies as they call them), through which the reservation values and/or the concession rate of its sub-negotiators could be controlled. Najjar et al [10] operated in a one-to-many multi-deal setting to investigate the problem of quality-ofexperience management. They propose a coordinator that can update its sub-negotiators' parameters, as well as take control of the bidding if a deal has not been reached near the deadline.…”

“…Note that, none of these works had at its focus integrating general bilateral strategies. Hence, their authors either adapted some simple time-based concession strategies for their subnegotiators [8], [10], [14], or picked bilateral strategies that could be adapted to fit the type of coordination they proposed [2], [9], [13]. Moreover, Williams et al [9] are the only to propose a coordinator that uses estimates, yet, their estimates are utility estimates and not outcome estimates as in our case.…”