As　the　number　of　devices　connected　to　the　Internet　of　things　(IoT)　surges,　the　amount　of　data　explodes.　Therefore　it　not　only　increases　the　bandwidth　load　of　data　transmission　but　also　aggravates　the　computing　and　storage　load　of　a　cloud　platform.　At　the　same　time,　the　traditional　computing　paradigm　centered　on　cloud　computing　cannot　meet　the　real-time　requirements　in　many　application　scenarios.　The　emergence　of　edge　computing　can　solve　the　problems　of　realtime　data　processing　and　network　bandwidth　occupation　in　the　current　IoT　scene.　In　this　paper,　according　to　the　characteristics　of　IoT,　such　as　fragmented　data,　heterogeneous　network,　and　limited　energy　consumption,　the　architecture　of　an　IoT　edge　computing　system　is　constructed　to　suit　better　an　IoT　scene.　In　addition,　the　application　of　edge　computing　key　technologies　such　as　virtualization,　edge　intelligence,　computing　offload,　collaborative　scheduling　and　micro-services　in　resource-constrained　IoT　scenarios　is　analyzed　in　detail.　Finally,　the　functions　and　application　of　energy　consumption　monitoring　and　optimization　to　a　central　air-conditioning　system　are　analyzed　and　summarized,　which　is　a　typical　application　of　edge　computing　in　the　context　of　the　IoT.　©　2020　IEEE.