Ground-based　Wide-Angle　Camera　array　(GWAC)　is　a　short　time-scale　survey　telescope　that　can　take　images　covering　a　field　of　view　of　over　5,　000　square　degrees　every　15　seconds　or　even　shorter.　One　scientific　missions　of　GWAC　is　to　accurately　and　quickly　detect　anomaly　astronomical　events.　For　that,　a　huge　amount　of　data　must　be　handled　in　real　time.　In　this　paper,　we　propose　a　new　time　series　analysis　model,　called　DARIMA　(or　Dynamic　Auto-Regressive　Integrated　Moving　Average),　to　identify　the　anomaly　events　that　occur　in　light　curves　obtained　from　GWAC　as　early　as　possible　with　high　degree　of　confidence.　A　major　advantage　of　DARIMA　is　that　it　can　dynamically　adjust　its　model　parameters　during　the　real-time　processing　of　the　time　series　data.　We　identify　the　anomaly　points　based　on　the　weighted　prediction　result　of　different　time　windows　to　improve　accuracy.　Experimental　results　using　real　survey　data　show　that　the　DARIMA　model　can　identify　the　first　anomaly　point　for　all　light　curves.　We　also　evaluate　our　model　with　simulated　anomaly　events　of　various　types　embedded　in　the　real　time　series　data.　The　DARIMA　model　is　able　to　generate　the　early　warning　triggers　for　all　of　them.　The　results　from　the　experiments　demonstrate　that　the　proposed　DARIMA　model　is　a　promising　method　for　real-time　anomaly　detection　of　short　time-scale　GWAC　light　curves.