Unmanned　aerial　vehicles　(UAVs)　have　been　widely　used　to　provide　enhanced　information　coverage　as　well　as　relay　services　for　ground　Internet-of-Things　(IoT)　networks.　Considering　the　substantially　limited　processing　capability,　the　IoT　devices　may　not　be　able　to　tackle　with　heavy　computing　tasks.　In　this　article,　a　multi-UAV-aided　mobile-edge　computing　(MEC)　system　is　constructed,　where　multiple　UAVs　act　as　MEC　nodes　in　order　to　provide　computing　offloading　services　for　ground　IoT　nodes　which　have　limited　local　computing　capabilities.　For　the　sake　of　balancing　the　load　for　UAVs,　the　differential　evolution　(DE)-based　multi-UAV　deployment　mechanism　is　proposed,　where　we　model　the　access　problem　as　a　generalized　assignment　problem　(GAP),　which　is　then　solved　by　a　near-optimal　solution　algorithm.　Based　on　this,　we　are　capable　of　achieving　the　load　balance　of　these　drones　while　guaranteeing　the　coverage　constraint　and　satisfying　the　quality　of　service　(QoS)　of　IoT　nodes.　Furthermore,　a　deep　reinforcement　learning　(DRL)　algorithm　is　conceived　for　the　task　scheduling　in　a　certain　UAV,　which　improves　the　efficiency　of　the　task　execution　in　each　UAV.　Finally,　sufficient　simulation　results　show　the　feasibility　and　superiority　of　our　proposed　load-balance-oriented　UAV　deployment　scheme　as　well　as　the　task　scheduling　algorithm.