In　recent　years,　the　smart　grid　has　been　recognized　as　an　important　form　of　the　Internet　of　Things　application.　In　the　smart　grid,　as　an　energy-based　cyber-physical　system,　the　advanced　metering　infrastructure　(AMI)　will　be　developed　to　monitor　and　control　the　power　grid　by　integrating　computing　and　networking　components　to　ensure　stable　and　efficient　operation.　The　AMI　is　vulnerable　to　cyber　attacks,　especially　data　integrity　attacks.　There　have　been　a　number　of　research　efforts　on　detecting　such　attacks.　Nonetheless,　most　of　existing　schemes　either　rely　on　predefined　thresholds　or　require　external　knowledge.　This　may　lead　to　low　detection　accuracy　when　the　thresholds　are　improperly　defined,　and　where　there　is　a　lack　of　the　external　knowledge.　To　address　these　issues,　in　this　paper,　we　propose　a　Gaussian-mixture　model-based　detection　scheme　to　mitigate　data　integrity　attacks.　Not　relying　upon　the　predefined　thresholds　or　external　knowledge,　our　developed　scheme　operates　through　narrowing　the　range　of　normal　data,　which　can　be　obtained　through　clustering　the　historical　data　and　learning　minimum　and　maximum　values　or　distance　values　to　each　center　of　individual　clusters.　To　evaluate　the　effectiveness　of　our　proposed　scheme,　we　conduct　performance　simulation　based　on　the　ElectricityLoadDiagrams20112014　data　set,　and　then　analyze　the　effectiveness　of　the　proposed　scheme　with　respect　to　detection　accuracy　and　overhead.　The　results　of　our　investigation　show　that　our　scheme　could　achieve　a　higher　detection　rate,　and　a　lower　error　rate,　in　comparison　to　existing　schemes　based　on　the　Min-Max　model.