Balancing energy demand and production is be-coming a more and more challenging task for energy utilities also because of the larger penetration of renewable energies which are more difficult to predict and control. While the traditional solution is to dynamically adapt energy production to follow time-varying demand, a new trend is to drive demand itself. Most of the ongoing actions in this direction involve greedy energy consumers, like industrial plants, supermarkets or large buildings. Pervasive communication technologies may allow in the near future to push further the granularity of such approach, by having the energy utility interacting with residen-tial appliances. In this paper we study large scale direct control of inelastic home appliances whose energy demand cannot be shaped, but simply deferred. Our solution does not suppose any particular intelligence at the appliances. The actuators are rather smart plugs—simple devices with local communication capabilities that can be inserted between appliances' plugs and power sockets and are able to interrupt/reactivate power flow through the plug. A simple control message can be broadcast to a large set of smart plugs for probabilistically enabling or deferring the activation requests of a specific load type in order to satisfy a probabilistic bound on the aggregated power consumption. The control law can be easily derived analytically.