Taking　the　latency,　energy　consumption　and　computing　resource　cost　into　consideration　comprehensively,　we　construct　a　single-cell,　multi-user　cloud-edge　collaborative　system　model　and　decompose　the　optimization　problem　of　task　offloading　and　resource　allocation　aiming　at　minimizing　the　total　user　overhead　into　three　sub-problems:　computing　resource　allocation,　uplink　power　allocation　and　task　offloading.　Computing　resource　and　uplink　power　allocation　are　optimized　by　using　convex　optimization　technique　and　bisection　method　respectively.　To　optimize　task　offloading,　we　propose　a　simulated　annealing-binary　particle　swarm　optimization　algorithm(SA-BPSO).　Simulation　results　show　that　SA-BPSO　can　better　reduce　the　total　user　overhead　compared　with　the　other　three　schemes　and　ensure　user　quality　of　service　quality.　©　2022　IEEE.