Energy & UtilitiesNACE D35Time Series Forecasting1-Minute Intervals Cadence60 Steps HorizonTarget:
target_0fev / AutoGluon ↗Boomlet Smart Meter Building Energy
High-frequency 1-minute smart meter electrical load benchmark spanning 35 sub-meter channels across commercial facility infrastructure with a 60-minute forecast horizon to optimize peak shaving and demand response.
16,384Records (Rows)
1Time Series
1-Minute IntervalsSampling Cadence
60 StepsForecast Horizon
Strong diurnal 24-hour cycle (1,440 timesteps) modulated by business-hour occupancy, scheduled compute batch processing, and thermal inertia decay.Dominant Seasonality
41 Methodsfev Leaderboard (SQL)
BUSINESS CONTEXT & OBJECTIVESmart Buildings & Energy Management (D35)
Business Objective: Boomlet Smart Meter Building Energy
01Business Context
Facility managers and commercial energy operators face steep demand charges and dynamic tariff spikes based on short-duration peak loads. Operating high-density compute, HVAC, and enterprise IT infrastructure requires continuous minute-by-minute visibility to orchestrate automated battery storage discharge, chiller sequencing, and dynamic load shed.
02Analytical Objective
Forecast 35 synchronized sub-meter active power channels over a rolling 60-minute ahead horizon (H=60) at 1-minute resolution.
03Economic & Decision Impact
Under-forecasting spikes incurs severe 15-minute peak ratchet tariffs and risks transformer tripping, while over-forecasting triggers unnecessary diesel generator spinning reserves or premature battery degradation costing tens of thousands in monthly OPEX.
ML Benchmark Narrative
Classical univariate statistical models like AutoARIMA and Seasonal Naive struggle with high-dimensional 35-channel inter-series cross-correlation and high-frequency noise at 1-minute sampling. Gradient-boosted trees (LightGBM) using multi-lag windowing capture static subsystem interactions effectively, but modern zero-shot foundation models such as Mistral's Timestral, TimesFM, and MOIRAI excel by modeling joint multi-channel attention and non-stationary load bursts without requiring local parameter re-fitting.
Source Origin:Building Data Genome 2 / Smart Meter Benchmark
Creator:Clayton Miller et al. (Building and Urban Data Science Lab, National University of Singapore) (2020)
License:CC-BY-4.0
Reference:Paper / Repo ↗
FEATURE SPECIFICATION & DATA DICTIONARY
Target & Feature Column Definitions
Exhaustive business definitions, measurement units, roles, and target variables across all 43 columns.
| Col | Variable / Feature Name | Role | Type | Unit / Scale | Description & Business Meaning |
|---|---|---|---|---|---|
| C | target_0Power Load Ch 0 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 0 |
| D | target_1Power Load Ch 1 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 1 |
| E | target_10Power Load Ch 10 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 10 |
| F | target_11Power Load Ch 11 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 11 |
| G | target_12Power Load Ch 12 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 12 |
| H | target_13Power Load Ch 13 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 13 |
| I | target_14Power Load Ch 14 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 14 |
| J | target_15Power Load Ch 15 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 15 |
| K | target_16Power Load Ch 16 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 16 |
| L | target_17Power Load Ch 17 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 17 |
| M | target_18Power Load Ch 18 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 18 |
| N | target_19Power Load Ch 19 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 19 |
| O | target_2Power Load Ch 2 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 2 |
| P | target_20Power Load Ch 20 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 20 |
| Q | target_21Power Load Ch 21 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 21 |
| R | target_22Power Load Ch 22 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 22 |
| S | target_23Power Load Ch 23 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 23 |
| T | target_24Power Load Ch 24 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 24 |
| U | target_25Power Load Ch 25 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 25 |
| V | target_26Power Load Ch 26 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 26 |
| W | target_27Power Load Ch 27 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 27 |
| X | target_28Power Load Ch 28 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 28 |
| Y | target_29Power Load Ch 29 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 29 |
| Z | target_3Power Load Ch 3 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 3 |
| AA | target_30Power Load Ch 30 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 30 |
| AB | target_31Power Load Ch 31 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 31 |
| AC | target_32Power Load Ch 32 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 32 |
| AD | target_33Power Load Ch 33 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 33 |
| AE | target_34Power Load Ch 34 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 34 |
| AF | target_4Power Load Ch 4 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 4 |
| AG | target_5Power Load Ch 5 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 5 |
| AH | target_6Power Load Ch 6 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 6 |
| AI | target_7Power Load Ch 7 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 7 |
| AJ | target_8Power Load Ch 8 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 8 |
| AK | target_9Power Load Ch 9 | TARGET | NUM | z-score kW | Standardized electrical power telemetry for sub-meter channel 9 |
| A | idBuilding ID | SERIES ID | CAT | — | Unique building and facility telemetry source identifier |
| B | timestampTimestamp | TIME | TIME | — | ISO 8601 recording timestamp sampled at 1-minute cadence |
| AL | typeFacility Type | Feature | CAT | — | Categorical facility primary usage and building classification code |
| AM | Application Usage | Feature | NUM | ratio | Binary flag or proportion allocated to enterprise application servers |
| AN | Infrastructure | Feature | NUM | ratio | Binary flag or proportion allocated to central facility infrastructure |
| AO | Database | Feature | NUM | ratio | Binary flag or proportion allocated to dedicated database clusters |
| AP | Networking | Feature | NUM | ratio | Binary flag or proportion allocated to network switches and routing gear |
| AQ | Security | Feature | NUM | ratio | Binary flag or proportion allocated to physical security and access control |
DATASET PREVIEW
Interactive Data Table
Explore rows, feature values, and target labels for Boomlet Smart Meter Building Energy.
TIME SERIES FORECASTING LEADERBOARD (FEV-BENCH)
Foundation Models vs Traditional ML & Baselines (41 Methods)
Empirical evaluation directly from the AutoGluon fev benchmark suite evaluating zero-shot foundation models against deep learning, gradient-boosted trees, and statistical baselines across 100 evaluation tasks.
#1 Global Ranked Model?Timestral-209M achieves the highest aggregate win rate (87.7%) across all 100 tasks in fev-bench.
Timestral-209M87.7% Win Rate • 0.51s latencyEvaluated Methods?41 models spanning open-weight foundation models, closed APIs, deep neural architectures, and statistical baselines.
41 MethodsMistral AI, Google, AWS, Salesforce, Prior LabsPrimary Evaluation Metric?Scaled Quantile Loss (SQL) penalizes both point prediction errors and quantile miscalibration across 9 probabilistic levels (p10 to p90).
SQL & MASEProbabilistic calibrationBrowser Execution?Carla Engine executes Timestral-123M 100% locally in-browser via WebGPU tensor kernels with zero server uploads.
100% WebGPUTimestral-123M • Zero server upload| Rank | Method / Model | Family | Organization | SQL Win Rate?Average win rate (%) against all competing models across the benchmark tasks under Scaled Quantile Loss. | SQL Skill?Normalized skill score relative to the Seasonal Naive baseline (0% = baseline, higher is better). | MASE Win Rate?Average win rate (%) under Mean Absolute Scaled Error. | Latency?Median end-to-end execution time per 100 time series in seconds. | Link |
|---|---|---|---|---|---|---|---|---|
| #1 | Timestral-209M | Foundation Model | Mistral AI | 87.7% | +50.4% | 86.0% | 0.51s | Repo ↗ |
| #2 | Timestral-123M (Carla Engine) | Foundation Model | Mistral AI | 86.8% | +50.2% | 85.0% | 0.32s | Repo ↗ |
| #3 | TimeRSI | Closed-Source API | GaTech & SamayLabs | 84.8% | +51.2% | 83.8% | 2512s | Repo ↗ |
| #4 | t0-gamma | Foundation Model | The Forecasting Company | 84.4% | +49.4% | 81.8% | 4.38s | Repo ↗ |
| #5 | Timestral-28M | Foundation Model | Mistral AI | 79.2% | +48.4% | 77.0% | 0.11s | Repo ↗ |
| #6 | timesfm-3 | Foundation Model | 78.5% | +49.0% | 77.0% | 3.41s | Repo ↗ | |
| #7 | ChakraTS | Baseline | Community | 78.2% | +48.1% | 79.5% | 14.22s | Repo ↗ |
| #8 | Lingjiang2.0 | Baseline | Community | 73.9% | +47.0% | 71.3% | 8.89s | Repo ↗ |
| #9 | Chronos-2 | Foundation Model | AWS | 70.4% | +47.3% | 68.4% | 0.84s | Repo ↗ |
| #10 | timeh2o-v1-tiny | Foundation Model | H2O.ai | 69.9% | +45.5% | 67.0% | 0.19s | Repo ↗ |
| #11 | Timestral-5M | Foundation Model | Mistral AI | 69.0% | +46.2% | 67.7% | 40ms | Repo ↗ |
| #12 | Toto-2.0-2.5B | Baseline | Community | 67.5% | +44.4% | 65.7% | 5.58s | Repo ↗ |
| #13 | t0-beta | Foundation Model | The Forecasting Company | 67.4% | +46.6% | 64.5% | 2.29s | Repo ↗ |
| #14 | Toto-2.0-1B | Baseline | Community | 66.4% | +44.4% | 65.5% | 2.48s | Repo ↗ |
| #15 | TiRex-2 | Foundation Model | NX-AI | 65.8% | +45.5% | 63.4% | 0.27s | Repo ↗ |
| #16 | Toto-2.0-313m | Baseline | Community | 65.1% | +44.2% | 63.5% | 1.06s | Repo ↗ |
| #17 | TiRex | Foundation Model | NX-AI | 58.0% | +42.6% | 54.1% | 0.24s | Repo ↗ |
| #18 | Toto-2.0-22m | Baseline | Community | 57.6% | +42.9% | 56.0% | 0.25s | Repo ↗ |
| #19 | TimesFM-2.5 | Baseline | Community | 54.6% | +42.2% | 53.5% | 1.87s | Repo ↗ |
| #20 | TabPFN-TS-3 | Foundation Model | Prior Labs | 52.4% | +43.1% | 51.3% | 235s | Repo ↗ |
| #21 | TS-ICL | Foundation Model | EDF-Lab | 51.2% | +43.1% | 49.8% | 2.49s | Repo ↗ |
| #22 | FlowState | Foundation Model | IBM | 49.3% | +39.9% | 49.9% | 2.29s | Repo ↗ |
| #23 | citras-fm | Foundation Model | Hitachi | 48.8% | +41.2% | 46.9% | 0.60s | Repo ↗ |
| #24 | Toto-1.0 | Baseline | Community | 47.5% | +40.8% | 45.9% | 22.35s | Repo ↗ |
| #25 | TabPFN-TS | Foundation Model | Prior Labs | 47.3% | +41.5% | 45.4% | 109s | Repo ↗ |
| #26 | Toto-2.0-4m | Baseline | Community | 46.2% | +40.7% | 43.6% | 0.20s | Repo ↗ |
| #27 | Moirai-2.0 | Baseline | Community | 41.9% | +39.3% | 40.5% | 0.35s | Repo ↗ |
| #28 | Chronos-Bolt | Foundation Model | AWS | 41.4% | +38.9% | 39.3% | 0.26s | Repo ↗ |
| #29 | TFT | Deep Learning | — | 31.7% | +32.2% | 29.2% | 829s | Repo ↗ |
| #30 | Stat. Ensemble | Baseline | Community | 27.5% | +20.7% | 30.6% | 147s | Repo ↗ |
| #31 | Sundial-Base | Foundation Model | Tsinghua University | 27.4% | +33.4% | 33.6% | 8.01s | Repo ↗ |
| #32 | PatchTST | Deep Learning | — | 26.8% | +30.1% | 25.1% | 664s | Repo ↗ |
| #33 | DeepAR | Deep Learning | — | 26.1% | +29.1% | 23.6% | 1113s | Repo ↗ |
| #34 | AutoARIMA | Statistical Baseline | — | 23.3% | +21.3% | 21.5% | 20.14s | Repo ↗ |
| #35 | AutoETS | Statistical Baseline | — | 20.3% | -26.8% | 22.5% | 3.48s | Repo ↗ |
| #36 | CatBoost | Tree Ensemble | — | 19.1% | +23.0% | 35.1% | 29.48s | Repo ↗ |
| #37 | LightGBM | Tree Ensemble | — | 17.8% | +21.0% | 33.1% | 3.03s | Repo ↗ |
| #38 | AutoTheta | Statistical Baseline | — | 15.6% | +5.5% | 19.8% | 3.28s | Repo ↗ |
| #39 | Seasonal Naive | Baseline | Community | 10.3% | 0.0% | 11.8% | 0.48s | Repo ↗ |
| #40 | Naive | Statistical Baseline | — | 6.7% | -45.4% | 10.9% | 0.47s | Repo ↗ |
| #41 | Drift | Statistical Baseline | — | 6.1% | -45.8% | 10.0% | 0.45s | Repo ↗ |
STATISTICAL DISTRIBUTIONS
Variable Schema & Summary Distributions
Observed numerical ranges, category cardinalities, missing rates, and sample values across 16,384 rows.
| Col | Variable Name | Type | Missing | Distinct | Summary Stats / Distribution | Sample Values |
|---|---|---|---|---|---|---|
| C | target_0TARGET | NUM | 0 | 538 | [-44.03004455566406, 28.61966323852539] μ=0.1 σ=1.1 | -0.6428920030593872-0.101332776248455050.10978353023529053 |
| D | target_1TARGET | NUM | 0 | 944 | [-14.359911918640137, 13.714910507202148] μ=0.0 σ=1.0 | -0.10237808525562286-0.2733895778656006-0.17911401391029358 |
| E | target_10TARGET | NUM | 0 | 1,448 | [-7.582956314086914, 15.162760734558105] μ=-0.0 σ=1.0 | -0.3245413899421692-0.302180290222167970.38206955790519714 |
| F | target_11TARGET | NUM | 0 | 1,365 | [-15.765235900878906, 22.846393585205078] μ=-0.0 σ=1.1 | -0.23570187389850616-0.71599674224853520.6048141717910767 |
| G | target_12TARGET | NUM | 0 | 304 | [-16.079328536987305, 17.41244125366211] μ=0.0 σ=1.0 | 0.042157437652349470.183264538645744320.21854130923748016 |
| H | target_13TARGET | NUM | 0 | 1,384 | [-15.527560234069824, 21.347028732299805] μ=-0.0 σ=1.0 | 0.25803303718566895-0.6974631547927856-0.12416543811559677 |
| I | target_14TARGET | NUM | 0 | 5,383 | [-4.225771903991699, 5.094090938568115] μ=0.0 σ=1.0 | 0.3796514570713043-1.0018651485443115-1.5816383361816406 |
| J | target_15TARGET | NUM | 0 | 5,538 | [-2.9093308448791504, 5.842514514923096] μ=-0.0 σ=1.0 | 1.2587755918502808-0.007539847400039434-0.5067351460456848 |
| K | target_16TARGET | NUM | 0 | 1,522 | [-9.381409645080566, 18.97089195251465] μ=-0.0 σ=1.0 | -0.5046837329864502-0.028080999851226807-0.34581616520881653 |
| L | target_17TARGET | NUM | 0 | 1,839 | [-3.541843891143799, 9.53619384765625] μ=-0.0 σ=1.0 | -0.3264339864253998-0.4465366005897522-0.24826067686080933 |
| M | target_18TARGET | NUM | 0 | 1,283 | [-6.183928966522217, 21.318506240844727] μ=-0.0 σ=1.0 | -0.68652325868606570.0068431952968239780.5186136960983276 |
| N | target_19TARGET | NUM | 0 | 2,016 | [-0.7927291989326477, 5.409099578857422] μ=-0.1 σ=1.0 | 5.3714194297790535.3893933296203615.366222381591797 |
| O | target_2TARGET | NUM | 0 | 12,157 | [-8.00523853302002, 4.782840728759766] μ=0.1 σ=1.0 | 0.51328885555267330.306554496288299560.14857825636863708 |
| P | target_20TARGET | NUM | 0 | 1,319 | [-19.653553009033203, 18.487762451171875] μ=-0.0 σ=1.0 | -0.102060064673423770.149980440735816960.03497166931629181 |
| Q | target_21TARGET | NUM | 0 | 1,917 | [-5.919212341308594, 5.917386531829834] μ=-0.0 σ=1.0 | -0.42948734760284424-0.41057056188583374-0.2439572960138321 |
| R | target_22TARGET | NUM | 0 | 747 | [-16.53339385986328, 33.12425231933594] μ=-0.0 σ=1.0 | -0.650463879108429-0.86941295862197880.2800695598125458 |
| S | target_23TARGET | NUM | 0 | 4,884 | [-5.264735221862793, 7.3459672927856445] μ=-0.1 σ=1.0 | 0.68749326467514040.69439834356307980.8113348484039307 |
| T | target_24TARGET | NUM | 0 | 534 | [-70.1915054321289, 19.822681427001953] μ=0.1 σ=1.4 | 0.033107496798038480.5090824365615845-0.4916854202747345 |
| U | target_25TARGET | NUM | 0 | 305 | [-5.317709922790527, 7.215456962585449] μ=-0.3 σ=1.4 | 0.0883571133017540.0883571133017541.1209766864776611 |
| V | target_26TARGET | NUM | 0 | 500 | [-11.043453216552734, 11.506114959716797] μ=0.0 σ=1.0 | -0.184705317020416260.15369746088981628-0.035409968346357346 |
| W | target_27TARGET | NUM | 0 | 1,207 | [-36.001251220703125, 11.55960464477539] μ=-0.0 σ=1.1 | 0.0428466759622097-0.17630717158317566-0.2747027575969696 |
| X | target_28TARGET | NUM | 0 | 4,274 | [-1.385882019996643, 2.6772077083587646] μ=-0.1 σ=1.0 | 0.60419827699661250.6174199581146240.6644302606582642 |
| Y | target_29TARGET | NUM | 0 | 284 | [-4.675403594970703, 5.30846643447876] μ=-0.3 σ=1.4 | 0.67677414417266850.2856534421443939-0.023126037791371346 |
| Z | target_3TARGET | NUM | 0 | 1,520 | [-10.004743576049805, 13.117582321166992] μ=-0.0 σ=1.0 | -0.4237118363380432-0.171601921319961550.033504460006952286 |
| AA | target_30TARGET | NUM | 0 | 8,540 | [-1.610131859779358, 2.497756004333496] μ=-0.1 σ=1.0 | 0.95970833301544190.86702555418014530.8468590974807739 |
| AB | target_31TARGET | NUM | 0 | 5,136 | [-3.5285274982452393, 5.009934425354004] μ=-0.0 σ=1.0 | -0.15996453166007996-0.20458126068115234-0.2545827627182007 |
| AC | target_32TARGET | NUM | 0 | 2,996 | [-5.469451904296875, 14.236705780029297] μ=0.1 σ=1.0 | -0.364301472902298-0.36003294587135315-0.3493616580963135 |
| AD | target_33TARGET | NUM | 0 | 1,086 | [-14.494296073913574, 16.24566078186035] μ=-0.0 σ=1.0 | -0.6814942955970764-0.186548277735710140.5292198061943054 |
| AE | target_34TARGET | NUM | 0 | 1,597 | [-6.253174781799316, 15.90526008605957] μ=-0.0 σ=1.0 | -0.592156708240509-0.65881288051605220.13153952360153198 |
| AF | target_4TARGET | NUM | 0 | 746 | [-38.18638610839844, 12.74746036529541] μ=-0.0 σ=1.0 | -0.46323299407958984-0.24244149029254913-0.5966278910636902 |
| AG | target_5TARGET | NUM | 0 | 14,494 | [-3.158867120742798, 6.317196846008301] μ=-0.0 σ=1.0 | 0.31170165538787840.33489838242530820.20818988978862762 |
| AH | target_6TARGET | NUM | 0 | 3,584 | [-5.986133575439453, 9.918814659118652] μ=-0.0 σ=1.0 | -0.7189429998397827-1.42519700527191160.06821408122777939 |
| AI | target_7TARGET | NUM | 0 | 1,226 | [-5.604093074798584, 31.262046813964844] μ=-0.0 σ=1.0 | -0.34483498334884644-0.111504971981048580.12649163603782654 |
| AJ | target_8TARGET | NUM | 0 | 12,617 | [-3.4503486156463623, 7.623702049255371] μ=0.0 σ=1.0 | 2.54499340057373052.82784271240234382.323232889175415 |
| AK | target_9TARGET | NUM | 0 | 962 | [-7.205317974090576, 4.0582780838012695] μ=-0.0 σ=1.0 | 0.256297111511230470.238089993596076970.31422892212867737 |
| A | id | CAT | 0 | 1 | — | 128212821282 |
| B | timestamp | CAT | 0 | 16,384 | — | 2024-06-01T00:01:002024-06-01T00:02:002024-06-01T00:03:00 |
| AL | type | CAT | 0 | 1 | — | rrr |
| AM | Application Usage | NUM | 0 | 1 | [1, 1] μ=1 σ=0 | 111 |
| AN | Infrastructure | NUM | 0 | 1 | [0, 0] μ=0 σ=0 | 000 |
| AO | Database | NUM | 0 | 1 | [0, 0] μ=0 σ=0 | 000 |
| AP | Networking | NUM | 0 | 1 | [0, 0] μ=0 σ=0 | 000 |
| AQ | Security | NUM | 0 | 1 | [0, 0] μ=0 σ=0 | 000 |
FREQUENTLY ASKED QUESTIONS
Frequently Asked Questions: Boomlet Smart Meter Building Energy
Common questions regarding the Boomlet Smart Meter Building Energy dataset, machine learning task formulations, and in-browser tabular inference.
What is the forecasting horizon for Boomlet Smart Meter Building Energy?
The benchmark evaluates a rolling 60-minute ahead horizon (60 steps at 1-minute cadence) aligned with commercial peak-shaving and hourly dispatch schedules.
Can I run zero-server forecasts on this dataset in Google Sheets?
Yes, Carla enables zero-server in-context time series forecasting directly in spreadsheets using Mistral's Timestral foundation model.
Which models perform best on Boomlet Smart Meter Building Energy?
Zero-shot foundation models such as Mistral's Timestral, TimesFM, and MOIRAI lead performance on multi-channel sub-meter telemetry by modeling cross-circuit correlations without local model re-training, closely followed by LightGBM lag ensembles.
LIVE EVALUATION IN GOOGLE SHEETS
Test TabICLv2 on Boomlet Smart Meter Building Energy Yourself
Open the pre-loaded Google Sheet and let Carla configure the target and task for local, zero-cloud tabular machine learning.
Step 1
Launch Carla
Click once to open the spreadsheet and Carla side panel together.
Step 2
Review the Setup
Carla selects the dataset target and task from this page automatically.
Step 3
Evaluate & Predict
Run predictions and compute metrics with zero server uploads.
Provenance & Attribution
Miller et al., The Building Data Genome 2 Project: An open dataset of electrical meter readings for 3,053 non-residential buildings, Scientific Data 2020.