ECoLAD: Deployment-Oriented Evaluation for Automotive Time-Series Anomaly Detection

TL;DR

ECoLAD (Efficiency Compute Ladder for Anomaly Detection), a deployment-oriented evaluation protocol instantiated as an empirical study on proprietary automotive telemetry and complementary public benchmarks, is presented.

Abstract

Time-series anomaly detectors are commonly compared on workstation-class hardware under unconstrained execution. In-vehicle monitoring, however, requires predictable latency and stable behavior under limited CPU parallelism. Accuracy-only leaderboards can therefore misrepresent which methods remain feasible under deployment-relevant constraints. We present ECoLAD (Efficiency Compute Ladder for Anomaly Detection), a deployment-oriented evaluation protocol instantiated as an empirical study on proprietary automotive telemetry (anomaly rate ${\approx}$0.022) and complementary public benchmarks. ECoLAD applies a monotone compute-reduction ladder across heterogeneous detector families using mechanically determined, integer-only scaling rules and explicit CPU thread caps, while logging every applied configuration change. Throughput-constrained behavior is characterized by sweeping target scoring rates and reporting (i) coverage (the fraction of entities meeting the target) and (ii) the best AUC-PR achievable among measured ladder configurations satisfying the target. On constrained automotive telemetry, lightweight classical detectors sustain both coverage and detection lift above the random baseline across the full throughput sweep. Several deep methods lose feasibility before they lose accuracy.

Figures (3)

• Figure 1: Throughput feasibility CDF under a fixed tier. Each curve shows the fraction of evaluated entities whose throughput exceeds a target threshold $\tau$, computed as $\mathrm{wps}=N/t_{\mathrm{inf}}$ (Sec. \ref{['sec:proxies']}). The horizontal line marks the 50% feasibility reference.
• Figure 2: Performance and throughput degradation across compute tiers (GPU $\rightarrow$ CPU-MT $\rightarrow$ CPU-LT $\rightarrow$ CPU-1T). (A) Mean AUC-PR per method at each tier. (B) Median throughput ($\mathrm{wps}$; log scale) from $t_{\mathrm{inf}}$ (Sec. \ref{['sec:proxies']}). (C) Relative AUC-PR change versus GPU (%).
• Figure 3: Mean achievable detection quality under throughput targets on the constrained (CPU-1T) tier. Columns are throughput targets $\tau$; rows are methods. Each cell reports the mean AUC-PR achievable while meeting $\tau$ using $t_{\mathrm{inf}}$ (Sec. \ref{['sec:proxies']}). Hatched cells indicate targets where coverage falls below 50% of entities.