SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.08337 · AAAI · 2025

Hierarchical Multi-Agent Framework for Carbon-Efficient Liquid-Cooled Data Center Clusters

Desik Rengarajan, Avisek Naug, Antonio Guillen, Vineet Gundecha, Sahand Ghorbanpour, Sajad Mousavi, Ashwin Babu, Soumyendu Sarkar, Ricardo Luna Gutie ´rrez, Cullen Bash

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 3 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2502.08337.json · badge: /api/ran/2502.08337.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
HewlettPackard/green-dcc canonical (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
FunctionStatusWhere it lives
calculate_hvac_reward Ran
ran on a synthesized input
HewlettPackard/green-dcc/train_hvac_ppo_agent.py
code served (permissive licence) · get_code("f41790f03aa1aec8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

# Build the info dict that calculate_hvac_reward expects
# The function calls info.get('dc_total_power_kW', 1000.0)
info = {
    'dc_total_power_kW': 750.5,
    'other_key': 'other_value'
}

# Define target_setpoint - a numeric setpoint temperature
target_setpoint = 22.5

# Define optional min_sp and max_sp parameters
min_sp = 18.0
max_sp = 27.0

ARGS = {
    'info': info,
    'target_setpoint': target_setpoint,
    'min_sp': min_sp,
    'max_sp': max_sp
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
construct_hvac_observation Ran
ran on a synthesized input
HewlettPackard/green-dcc/train_hvac_ppo_agent.py
code served (permissive licence) · get_code("911baf03c46e6774")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (6,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Construct valid arguments for construct_hvac_observation

# env_info: dict with 'dc_exterior_ambient_temp' key
env_info = {
    'dc_exterior_ambient_temp': 22.5,
    'other_key': 'other_value'
}

# current_setpoint: float representing temperature setpoint in Celsius
current_setpoint = 23.0

# cpu_load: float representing CPU utilization (0.0 to 1.0)
cpu_load = 0.65

# gpu_load: float representing GPU utilization (0.0 to 1.0)
gpu_load = 0.45

# current_hour: int or float representing hour of day (0-23)
current_hour = 14

# obs_dim: int representing observation dimension (must match number of features)
# The function constructs: [sin_hour, cos_hour, ambient_temp, cpu_load, gpu_load, current_setpoint]
# That's 6 features, so obs_dim must be 6
obs_dim = 6

ARGS = {
    'env_info': env_info,
    'current_setpoint': current_setpoint,
    'cpu_load': cpu_load,
    'gpu_load': gpu_load,
    'current_hour': current_hour,
    'obs_dim': obs_dim
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (6,) — shape (6,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_driving_inputs Ran
ran on a synthesized input
HewlettPackard/green-dcc/train_hvac_ppo_agent.py
code served (permissive licence) · get_code("f15bd22a179bd1d1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

class TimeManager:
    def __init__(self):
        self.step_count = 0
    
    def step(self):
        day = self.step_count % 7
        hour = (self.step_count % 24)
        time_features = np.array([day, hour, 0.5, 0.3])
        manager_done = False
        return day, hour, time_features, manager_done

class WeatherManager:
    def __init__(self):
        self.step_count = 0
    
    def step(self):
        ambient_temp = 20.0 + 5.0 * np.sin(self.step_count / 10.0)
        humidity = 0.6
        wet_bulb = 15.0 + 3.0 * np.sin(self.step_count / 10.0)
        pressure = 101325.0
        return ambient_temp, humidity, wet_bulb, pressure

config = {
    'load_profile': 'sinusoidal'
}

ARGS = {
    'step': 0,
    't_manager': TimeManager(),
    'w_manager': WeatherManager(),
    'config': config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
str2bool Ran
ran, violated the contract we drafted
HewlettPackard/green-dcc/train_SAC_agent.py
pointer only (licence: MIT); the stored copy get_code serves, from softrepa/SoftREPA, is pointer only (licence: NONE) · get_code("3574b3bb42395a32")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from softrepa/SoftREPA, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
str2bool 6 other papers
1 dated earlier, 4 later, 1 same year, order not determinable
2405.06573 (2024-05)
An Investigation of Incorporating Mamba for Speech Enhancement
2025.findings-emnlp.598 (2025 (year only))
MMATH: A Multilingual Benchmark for Mathematical Reasoning
2503.08250 (2025-03)
Aligning Text to Image in Diffusion Models is Easier Than You Think
and 3 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Reducing the environmental impact of cloud computing requires efficient workload distribution across geographically dispersed Data Center Clusters (DCCs) and simultaneously optimizing liquid and air (HVAC) cooling with time shift of workloads within individual data centers (DC). This paper introduces Green-DCC, which proposes a Reinforcement Learning (RL) based hierarchical controller to optimize both workload and liquid cooling dynamically in a DCC. By incorporating factors such as weather, carbon intensity, and resource availability, Green-DCC addresses realistic constraints and interdependencies. We demonstrate how the system optimizes multiple data centers synchronously, enabling the scope of digital twins, and compare the performance of various RL approaches based on carbon emissions and sustainability metrics while also offering a framework and benchmark simulation for broader ML research in sustainability.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2502.08337")
get_code_for_paper("2502.08337")
have("2502.08337")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2502.08337.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2502.08337.svg)](https://syntology.ai/paper/2502.08337)

Connect an agent — have() is free.