ORIGINAL RESEARCH article
Front. Sustain. Cities
Sec. Smart Technologies and Cities
A Unified Framework for Design of Forecast-Adaptive and Regime-Aware ICT Design for Smart Waste Collection
PRADEEP BEDI 1
Sanjoy Das 2
Devesh Pratap Singh 1
Indrani Das 3
1. Graphic Era Deemed to be University, Dehradun, India
2. Regional Campus Manipur, Indira Gandhi National Tribal University, Amarkantak, India
3. Assam University, Silchar, India
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Abstract
IoT-enabled smart waste collection is typically evaluated through operational savings while the electricity uses and emissions of the enabling digital infrastructure are rarely quantified. This paper presents a unified, and resource-aware evaluation framework that computes a net environmental balance by jointly accounting for operational impacts and end-to-end ICT energy and 𝐶𝑂2 across device, network, edge, and cloud layers. To ground the assessment in realistic urban conditions, daily atmospheric context is constructed from Sentinel-5P Level-3 time series over New Delhi taken from 2020 to 2025 using UV Aerosol Index, CO, and NO2. After QA-masked compositing and preprocessing, pollution regimes are learned via standardized multivariate clustering and evolved with a Markov scenario generator. Multi-horizon forecasting with 7-day and 30-day is then compared across ARIMA, Ridge Regression, Random Forest, Gradient Boosting, and LSTM to estimate the risk to drive a forecast-adaptive ICT policy that tunes sensing/communication rates. Results show ensemble learners provide the strongest forecasting accuracy across pollutants, while the adaptive ICT design reduces average ICT emissions that shows measurable, regime-aware energy and CO2 savings without sacrificing predictive capability for city-scale evaluation.
Summary
Keywords
clustering, Forecast-adaptive ICT, Multi-horizon time-series forecasting, Pollution Regime, remote sensing, Sentinel-5p, Smart waste collection
Received
30 December 2025
Accepted
17 February 2026
Copyright
© 2026 BEDI, Das, Singh and Das. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: PRADEEP BEDI; Sanjoy Das
Disclaimer
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.