With　the　continuous　development　of　the　Internet,　the　need　to　optimize　the　network　structure　and　ensure　its　stable　operation　has　become　a　pressing　issue　in　the　network.　Consequently,　accurate　and　real-time　network　traffic　prediction　models　play　a　crucial　role　in　network　optimization.　Although　there　are　various　series　of　data　prediction　models,　they　still　perform　poorly　in　real-time　network　traffic　prediction　because　network　traffic　is　often　non-stationary.　This　paper　aims　to　use　deep　learning　models　for　network　traffic　prediction,　especially　for　non-stationary　network　traffic　data.　Using　a　combination　of　the　Reversible　instance　normalization　(RevIN)　method　and　the　Long　Short　Term　Memory　(LSTM)　model　and　adding　a　Self-Attention　layer　can　enhance　the　model＇s　ability　to　capture　long-term　features.　Also,　an　offset　in　the　distribution　between　the　lookback　window　and　the　horizon　window　is　considered　in　the　model.　The　experimental　results　show　that　the　model　outperforms　previous　research　methods　on　the　task　of　non-stationary　network　traffic　prediction,　which　provides　an　important　reference　for　optimizing　the　network.　©　2023　ACM.