We present results from experiments where the effects of flow control at a single substation are compared to distributed flow control at multiple substations. The latter approach is made possible by equipping individual substations with some computing power and integrating them into a communications network. Software agents, who cooperate with other software agents (substations) and invoke time limited reductions to consumption, are embedded in each substation. The experiments show that it is possible to automatically load balance a small district heating network using agent technology, e.g., to perform automatic peak clipping and load shifting.