Atomic Dynamic Flow Games: Adaptive vs. Nonadaptive Agents

We propose a game model for selfish routing of atomic agents, who compete for use of a network to travel from their origins to a common destination as quickly as possible. We follow a frequently used rule that the latency an agent experiences on each edge is a constant transit time plus a variable waiting time in a queue. A key feature that differentiates our model from related ones is an edge-based tie-breaking rule for prioritizing agents in queueing when they reach an edge at the same time. We study both nonadaptive agents (each choosing a one-off origin–destination path simultaneously at the very beginning) and adaptive ones (each making an online decision at every nonterminal vertex they reach as to which next edge to take). On the one hand, we constructively prove that a (pure) Nash equilibrium (NE) always exists for nonadaptive agents and show that every NE is weakly Pareto optimal and globally first-in first-out. We present efficient algorithms for finding an NE and best responses of nonadaptive agents. On the other hand, we are among the first to consider adaptive atomic agents, for which we show that a subgame perfect equilibrium (SPE) always exists and that each NE outcome for nonadaptive agents is an SPE outcome for adaptive agents but not vice versa.

Selfishness Need Not Be Bad

The price of anarchy (PoA) is a standard measure for the inefficiency of selfish routing in the static Wardrop traffic model. Empirical studies and a recent analysis reveal a surprising property that the PoA tends to one when the total demand T gets large. These results are extended by a new framework for the limit analysis of the PoA in arbitrary nonatomic congestion games that apply to arbitrary growth patterns of T and all regularly varying cost functions. For routing games with Bureau of Public Road (BPR) cost functions, the convergence follows a power law determined by the degree of the BPR functions, and a related conjecture need not hold. These findings are confirmed by an empirical analysis of traffic in Beijing.

Constraint Games for Stable and Optimal Allocation of Demands in SDN

Software Defined Networking (or SDN) allows to apply a centralized control over a network of computers in order to provide better global throughput. One of the problem to solve is the multi-commodity flow routing where a set of demands (or commodities) have to be routed at minimum cost. In contrast with other versions of this problem, we consider here problems with congestion that change the cost of a link according to the capacity used. We propose here to study centralized routing with Constraint Programming and selfish routing with Constraint Games. Selfish routing reaches a Nash equilibrium and is important for the perceived quality of the solution since no user is able to improve his cost by changing only his own path. We present real and synthetic benchmarks with hundreds or thousands players and we show that for this problem the worst selfish routing is often close to the optimal centralized solution.