In this paper, the problem of how to balance the energy consumption during data processing in networks is investigated using a fog middleware. We first demonstrate that for a fog network with different kind of nodes, balancing the energy relies on a combinatorial optimization that is solved using graph theory. We propose a transformation of the transshipment graph problem to formulate an optimization problem that we solve with linear programming (LP). We show the possibility of balancing and extending the battery life of the whole network based on cooperation between nodes without jeopardizing individual nodes’ battery life. We use both, emulation and real scenarios to test our optimization algorithm. We show we can balance the network energy, keep all nodes alive and active  95% of the time.