Training and inference are only part of the bill. eCAL is the first metric that adds up the + energy of data collection, preprocessing, training, evaluation, and inference — end to end, in Joules per bit — + so you can see the true cost of adding AI to a communication system.
+ + +ecal-energy) — the same case-study configuration and the same sampled inference counts (γ = 10²…10⁸) as the paper's Fig. 13.Telecom metrics stop at the network. Deep-learning metrics stop at the model. No one connects + the two — so nobody can say what it actually costs, in energy, to make a communication system intelligent.
+Energy-per-Bit, PUE, CUE, and WUE measure the network and data-center layer with precision — but they have no notion of what the AI model on top is actually computing.
+APC, APEC, TTCAPC, and TTCAPEC weigh model accuracy against training or inference cost — but most don't even cover inference, and none account for the energy spent collecting the data in the first place.
+Without a metric spanning the full OSI-to-MLOps pipeline, nobody can compare the true energy cost of "adding intelligence" to a network, or predict how that cost falls as a model is used more.
+eCAL formalizes every stage of the AI lifecycle as a standard OSI/MLOps data-manipulation + component, then reduces the whole pipeline to one closed-form number in Joules per bit.
+A formal breakdown of data collection, preprocessing, training, evaluation, and inference as standardized OSI and MLOps "data manipulation components" — the shared vocabulary the rest of eCAL builds on.
Closed-form energy formulas across all 7 OSI layers — retransmission rates, protocol overheads, wired and wireless links — validated against real Wi-Fi 6 and 5G measurement studies.
Exact FLOP formulas for MLP, CNN, KAN, and Transformer models, mapped to real hardware power and FLOPS profiles — from an Apple M2 to an NVIDIA H100 — with pluggable support for ResNet, VGG, and Baichuan-style LLMs.
A single closed-form J/bit expression spanning the whole lifecycle, shipped as a modular, extensible Python package — pip install ecal-energy — with both a CLI and an API.
eCAL reduces data collection, preprocessing, training, evaluation, and inference to a single + Joules-per-bit number — so the cost of developing a model and the cost of running it can be compared on the + same scale.
+ED is the one-time development energy — data collection, preprocessing, training, and + evaluation. Einf,p is the energy of a single inference pass. γ is how many times the deployed + model is actually run; γᵥ captures virtualization overhead. f, IS, NS, and NI,P + normalize everything to Joules per bit of data processed.
+Validated against real Wi-Fi 6 and 5G measurement datasets, where eCAL acts as a tight upper bound on observed energy cost.
+Grounded in a formal lifecycle methodology, validated against real network measurement + studies, and open-sourced as a working tool — not just a paper.
+Introduces eCAL, the first metric to span the full AI lifecycle — data collection, preprocessing, + training, evaluation, and inference — in a single Joules-per-bit number, validated on a real case-study + pipeline and against Wi-Fi 6 / 5G measurement data.
+ecal-energy)Applies the eCAL lifecycle methodology to O-RAN AI/ML workflows, quantifying the energy footprint of + adding machine learning to next-generation radio access networks.
+The earliest work in this research line, arguing for standardized, lifecycle-aware energy-efficiency + metrics as AI becomes native to 6G and future communication networks.
+eCAL ships as an open-source Python package with a CLI and an API — plug in your architecture, + hardware, and dataset size, and get a J/bit estimate in seconds.
+$ pip install ecal-energy +$ ecal estimate --model MLP --layers 3 --epochs 50 --hardware apple_m2+
import ecal + +result = ecal.estimate( + model_type="MLP", + model_params={"num_layers": 3, "din": 10, "dout": 2}, + num_samples=1000, num_epochs=50, + hardware="apple_m2", +) +print(result["ecal_j_per_bit"])+
ecal-energyEstimate the full lifecycle cost of a model — not just training, not just inference — before committing hardware or bandwidth to it.
MLP, CNN, KAN, or Transformer — eCAL puts every architecture on the same J/bit scale, so efficiency claims can be compared directly instead of by proxy.
Open-source and modular: plug in custom protocols, architectures, or hardware profiles instead of being limited to what ships out of the box.
Whether you're building energy-aware AI systems, researching sustainable networking, or want to extend + eCAL to a new architecture or protocol — we'd like to hear from you.
+ +