Electricity　theft　causes　substantial　economic　losses　and　safety　hazards.　While　the　widespread　adoption　of　advanced　metering　infrastructure　has　significantly　reduced　electricity　theft,　perpetrators　continue　to　find　ways　to　exploit　the　system,　employing　increasingly　covert　and　intricate　methods.　To　address　the　ongoing　challenge,　this　paper　proposes　an　attention　mechanism　optimized　multi-temporal　granularity　feature　driven　convolutional　ensemble　model　for　enhanced　accuracy　and　robustness　in　electricity　theft　detection　(ETD).　For　comprehensive　feature　extraction　across　diverse　temporal　scales,　the　proposed　framework　integrates　two　specialized　feature　extraction　modules.　The　first　module,　a　squeeze-and-excitation　network-optimized　temporal　convolutional　network,　selectively　focuses　on　informative　temporal　features　within　the　electricity　consumption　data.　The　second　module,　a　dual-dimensional　attention　enhanced　deep　residual　network　composed　of　residual　blocks　embedded　with　the　convolutional　block　attention　module,　facilitates　the　model＇s　concurrent　learning　of　informative　spatial　and　temporal　features.　Then,　the　features　from　each　module　are　fused　and　classified　through　a　fully　connected　layer.　To　validate　the　effectiveness　of　the　proposed　ETD　method,　this　paper　conducted　simulation　experiments　using　the　publicly　available　dataset　from　the　State　Grid　Corporation　of　China.　The　experimental　results　show　that　the　model　optimized　with　the　attention　mechanism　significantly　improves　the　performance　of　ETD.　Compared　to　other　ETD　models,　the　proposed　model　performs　excellently　in　various　indicators　under　different　training　set　ratios　and　sample　imbalance　scenarios,　demonstrating　good　generalization　and　robustness.　Additionally,　the　model　was　deployed　on　a　Raspberry　Pi　edge　computing　device　to　further　verify　its　feasibility　in　practical　engineering　applications.　©　2025　Elsevier　Ltd