target_0fev / AutoGluon ↗BizITobs Cloud Infrastructure Telemetry
High-resolution cloud infrastructure telemetry benchmark tracking 7 multivariate operational metrics for a critical enterprise cluster over a 24-hour horizon (288 steps at 5-minute intervals) to preempt outages and optimize autoscaling.
Business Objective: BizITobs Cloud Infrastructure Telemetry
01Business Context
Modern cloud-native microservices and mission-critical enterprise clusters generate telemetry at high velocity, requiring infrastructure engineering and Site Reliability Engineering (SRE) teams to make proactive capacity allocation and pod autoscaling decisions across daily diurnal cycles.
02Analytical Objective
Forecast 7 core infrastructure telemetry metrics simultaneously over a 288-step (24-hour) horizon at 5-minute cadence to anticipate system saturation and SLA degradation before outages occur.
03Economic & Decision Impact
Under-forecasting resource demand triggers severe latency spikes, cascading service timeouts, customer SLA penalties, and potential unplanned downtime; over-forecasting results in excessive cloud node provisioning and inflated infrastructure overhead.
04Temporal Dynamics & Covariate Information Flow
Operates without explicit scheduled calendar markers or external telemetry; models must capture intrinsic autoregressive feedback loops, burst traffic spikes, and coupled inter-metric relationships directly from the historical series.
Classical univariate baselines like AutoARIMA and Exponential Smoothing struggle with the long 288-step horizon and cross-series correlations across the seven telemetry streams. Feature-engineered gradient boosted tree models (such as LightGBM multi-output lag regressors) establish strong point forecast baselines, while zero-shot foundation models (including Mistral's Timestral, TimesFM, and MOIRAI) deliver superior in-context transfer by capturing complex multi-rate temporal dynamics without requiring custom hyperparameter tuning.
Target & Feature Column Definitions
Exhaustive business definitions, measurement units, roles, and target variables across all 9 columns.
Known Future Covariates vs. Historically Observed Covariates
Multi-step forecasting models must respect the arrow of time and real-world information availability. FEV benchmarks and Carla strictly distinguish between features known across the forward prediction window versus realizations available only up to the forecast origin.
Scheduled promotions (such as Rossmann's Promo), calendar events (school/state holidays), and operational forecasts (such as Nord Pool's day-ahead grid load and wind power forecasts). These are deterministic or published before market clearing, allowing foundation models to legitimately condition on them across future steps.
Stochastic operational observations (such as Rossmann's actual customer footfall Customers, Rohlik's actual precipitation and snowfall, or sudden warehouse shutdowns). Because these are only realized in real-time, future values must never enter a prediction to prevent lookahead target leakage.
| Col | Variable / Feature Name | Role | Type | Unit / Scale | Description & Business Meaning |
|---|---|---|---|---|---|
| C | target_0CPU Utilization | TARGET | NUM | ratio | Normalized CPU compute load across provisioned virtual processor cores |
| D | target_1Memory Pressure | TARGET | NUM | ratio | Proportional consumption of allocated system RAM and container memory buffers |
| E | target_2Disk I/O Throughput | TARGET | NUM | MB/s | Rate of persistent storage input/output throughput and block storage operations |
| F | target_3Network Traffic Volume | TARGET | NUM | Mbps | Combined ingress and egress network throughput across cluster interfaces |
| G | target_4Request Latency | TARGET | NUM | ms | Mean end-to-end service response duration for routed HTTP/RPC transactions |
| H | target_5Transaction Throughput | TARGET | NUM | req/s | Volume of completed incoming business requests processed per unit time |
| I | target_6Service Error Count | TARGET | NUM | count | Frequency of observed 5xx HTTP response codes and unhandled application runtime exceptions |
| A | idCluster Identifier | SERIES ID | CAT | — | Unique categorical identifier representing the specific monitored cluster or compute node partition |
| B | timestampTimestamp | TIME | TIME | — | 5-minute interval timestamp tracking continuous telemetry collection across the observation window |
Interactive Data Table
Explore rows, feature values, and target labels for BizITobs Cloud Infrastructure Telemetry.
Foundation Models vs Traditional ML & Baselines (41 Methods)
Empirical evaluation directly from the AutoGluon fev benchmark suite. Global aggregate ranking: The win rates and skill scores below represent cross-dataset performance across all 100 standardized tasks in fev-bench, rather than results isolated to BizITobs Cloud Infrastructure Telemetry.
| 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. | FEV Latency?FEV benchmark reference latency measured in server Python (median seconds per 100 series). Independent in-browser WebGPU execution for Carla is reported in the telemetry card above. | Link |
|---|---|---|---|---|---|---|---|---|
| #1 | Timestral-209M | Foundation Model | Mistral AI | 87.7% | +50.4% | 86.1% | 0.51s | Repo ↗ |
| #2 | Timestral-123M (Carla Engine) | Foundation Model | Mistral AI | 86.9% | +50.2% | 85.0% | 0.32sPython (FEV) | 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 | 78.6% | +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% | 67.1% | 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% | 65.6% | 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 | 58.1% | +42.6% | 54.2% | 0.24s | Repo ↗ |
| #18 | Toto-2.0-22m | Baseline | Community | 57.7% | +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% | 25.2% | 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 | — | 19.2% | +23.0% | 35.1% | 29.48s | Repo ↗ |
| #37 | LightGBM | Tree Ensemble | — | 17.8% | +21.0% | 33.2% | 3.03s | Repo ↗ |
| #38 | AutoTheta | Statistical Baseline | — | 15.6% | +5.5% | 19.8% | 3.28s | Repo ↗ |
| #39 | Seasonal Naive | Baseline | Community | 10.4% | 0.0% | 11.9% | 0.48s | Repo ↗ |
| #40 | Naive | Statistical Baseline | — | 6.7% | -45.4% | 11.0% | 0.47s | Repo ↗ |
| #41 | Drift | Statistical Baseline | — | 6.1% | -45.8% | 10.0% | 0.45s | Repo ↗ |
Variable Schema & Summary Distributions
Observed numerical ranges, category cardinalities, missing rates, and sample values across 31,968 rows.
| Col | Variable Name | Type | Missing | Distinct | Summary Stats / Distribution | Sample Values |
|---|---|---|---|---|---|---|
| C | target_0TARGET | NUM | 0 | 1,541 | [0, 49.04999923706055] μ=16.2 σ=10.3 | 000 |
| D | target_1TARGET | NUM | 0 | 57 | [0, 56] μ=9.7 σ=9.7 | 000 |
| E | target_2TARGET | NUM | 0 | 49 | [0, 48] μ=17.5 σ=13.6 | 000 |
| F | target_3TARGET | NUM | 0 | 27 | [0, 26] μ=3.2 σ=3.7 | 000 |
| G | target_4TARGET | NUM | 0 | 81 | [0, 82] μ=12.9 σ=12.9 | 000 |
| H | target_5TARGET | NUM | 0 | 121 | [0, 121] μ=21.8 σ=20.5 | 000 |
| I | target_6TARGET | NUM | 0 | 81 | [0, 80] μ=25.1 σ=19.1 | 000 |
| A | id | CAT | 0 | 1 | — | L2CL2CL2C |
| B | timestamp | CAT | 0 | 31,968 | — | 2020-11-01T00:00:002020-11-01T00:05:002020-11-01T00:10:00 |
Frequently Asked Questions: BizITobs Cloud Infrastructure Telemetry
Common questions regarding the BizITobs Cloud Infrastructure Telemetry dataset, machine learning task formulations, and in-browser tabular inference.
What is the forecasting horizon for BizITobs Cloud Infrastructure Telemetry?
The standard forecasting horizon is 288 time steps, corresponding to an exact 24-hour operational window evaluated at 5-minute sampling resolution.
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 without requiring backend ML pipelines.
Which models perform best on BizITobs Cloud Infrastructure Telemetry?
Pretrained zero-shot foundation models like Mistral's Timestral and lag-engineered LightGBM ensembles deliver superior accuracy on this benchmark by effectively capturing multi-target diurnal patterns.
Forecast with Carla: BizITobs Cloud Infrastructure Telemetry
Open the pre-loaded Google Sheet and let Carla generate multi-step probabilistic forecasts using Mistral's Timestral directly inside your browser with zero server uploads.
Launch Carla
Click once to open the spreadsheet and Carla side panel together.
Review the Setup
Carla auto-detects the target sequence, frequency cadence, and temporal covariates.
Forecast & Calibrate
Generate multi-step quantile forecasts with zero server uploads.
Provenance & Attribution
BizITobs IT Operations Telemetry Benchmark, AutoGluon TimeSeries 2024.