We introduce a decentralized and online path planning technique for a network of unmanned aerial vehicles (UAVs) in the presence of weather disturbances. In our problem setting, the group of UAVs are required to collaboratively visit a set of goals scattered in a 2-dimensional area. Each UAV will have to spend energy to reach these goals, but due to unforeseen disturbances, the required energy may vary over time and does not necessarily conform with the initial forecast and/or pre-computed optimal paths. Thus, we are dealing with two fundamental interrelated problems to find a global optimum at each point of time: (1) energy consumption prediction based on disturbances and, hence, online path replanning, and (2) distributed agreement among all UAVs to divide the remaining unvisited goals based on their positions and energy requirements. Our approach consists of four main components: (i) a distributed algorithm that periodically divides the unvisited goals among all the UAVs based on the current energy requirements of the UAVs, (ii) a local (i.e., UAV-level) $\AStar$-based algorithm that computes the {\em desirable} path for each UAV to reach the nodes assigned to it, (iii) a local PID controller that {\em predicts} the inputs to the UAV (i.e., thrust and moments), and (iv) a planner that computes the required energy and the replanning time period. We validate our proposed solution through a rich set of simulations and show that our approach is significantly more efficient than a best-effort algorithm that directs each idle UAV to visit the closest unvisited goal.