In this paper, we propose a novel architecture to estimate external forces applied to a compliantly controlled balancing robot in simulations. We use similar dynamics equations used in the controller to find mismatches in the available sensory data and associate them to an unknown external force. Then by decomposing Jacobians, we search over the surface of all body links in the robot to find the force application point. By approximating link geometries with ellipsoids, we can derive analytic solutions to solve the search problem very fast in real time. The proposed approach is tested on a complex humanoid robot in simulations where it outperforms static estimators over fast dynamic motions. We foresee a lot of applications for this method especially in human-robot interactions where it can serve as a whole body virtual suit of tactile sensors. It can also be very useful in identifying the inertial properties of objects being manipulated or mounted on the robot like a backpack.