A　growing　number　of　global　companies　select　Green　Cloud　Data　Centers　(GCDCs)　to　manage　their　delay-constrained　applications.　The　fast　growth　of　users＇　tasks　dramatically　increases　the　energy　consumed　by　GCDC,　e.g.,　Google.　The　random　nature　of　tasks　brings　a　big　challenge　of　scheduling　tasks　of　each　application　with　limited　infrastructure　resources　of　GCDCs.　This　work　accurately　computes　a　mathematical　relation　between　task　service　rates　and　the　number　of　tasks　refusal　in　GCDC.　Besides,　it　proposes　a　Temporal　Task　Scheduling　(TTS)　algorithm　investigating　the　temporal　variation　in　geo-distributed　cloud　data　centers　to　schedule　all　tasks　within　their　delay　constraints.　Furthermore,　a　novel　dynamic　hybrid　meta-heuristic　algorithm　is　developed　for　the　formulated　profit　maximization　problem,　based　on　genetic　simulated　annealing　and　particle　swarm　optimization.　The　proposed　algorithm　can　guarantee　that　differentiated　service　qualities　can　be　provided　with　higher　overall　performance　and　lower　energy　cost.　Trace-driven　simulations　demonstrate　that　larger　throughput　and　profit　is　achieved　than　several　existing　scheduling　algorithms.