[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122540-en":3,"doc-seo-122540-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122540,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","FastML-GA - FPGA-accelerated machine learning for realtime energy HVAC optimization in buildings","Fast machine learning (FastML) is presented to improve energy optimization and operational efficiency in building heating, ventilation, and air conditioning (HVAC) within building management systems (BMS). The approach replaces static schedule control and CPU-heavy optimization with a hybrid PS–PL design: a random forest surrogate model accelerated on FPGA programmable logic and a lightweight adaptive genetic algorithm (GA) running on the processor system. In a 72-day, four-season case study, it delivers over 1.67 million predictions per second on PYNQ-Z1, with electricity savings above 50% and daily thermal energy reductions up to 150 kWh during heating while keeping comfort within PMV thresholds.","ORIGINAL ARTICLE  \nFastML-GA: FPGA-accelerated machine learning for realtime energy HVAC optimization in buildings  \nMohammed Mshragi · Ioan Petri  \nReceived: 17 July 2025 / Accepted: 8 November 2025 © The Author(s) 2026  \nAbstract  \nFast machine learning (FastML) has strong potential to enhance energy optimization and operational efficiency in heating, ventilation, and air conditioning (HVAC) systems within building management systems (BMS) . Traditional HVAC control approaches frequently depend on static schedules and computationally intensive, CPU-based optimization techniques, which often lack the responsiveness and scalability required for realtime embedded applications. To address these limitations, we propose a fast machine learning framework that integrates a random forest surrogate model implemented as a hardware accelerator on the programmable logic (PL) with a lightweight and adaptive genetic algorithm (GA) executed on the processing system (PS), thereby forming a hybrid PS–PL deployment. This combination of fast machine learning and evolutionary algorithms optimization delivers substantial computational efficiency, achieving over 1.67 million predictions per second on a PYNQ-Z1 FPGA and significantly outperforming recent FPGA-based approaches. By using a case study, we demonstrate how FastML can employ a GA multi-objective fitness function to dynamically optimize hourly airflow rates and supply air temperatures in response to occupancy and seasonal environmental patterns, thereby reducing electricity and thermal energy consumption while maintaining occupant comfort within standard predicted mean vote (PMV) thresholds. Empirical evaluation conducted over 72 days across four distinct seasons reveals consistent electricity savings exceeding 50%, alongside thermal energy reductions of up to 150 kWh per day during heating periods. A comprehensive three-dimensional Pareto front analysis further substantiates the system’s capability to effectively balance energy efficiency and occupant comfort. These results highlight the practicality, scalability, and substantial promise of FPGA-based multi-objective optimization as a robust, real-time solution for intelligent and sustainable building energy management at the edge.  \nKeywords Fast machine learning · Genetic algorithms · Building management systems · Energy efficiency · Optimisation  \nAbbreviations  \nAFR  \nAT  \nAXI  \nBMS  \nBRAM  \nAir flow rate  \nAir temperature  \nAdvanced eXtensible interface Building management system Block random-access memory  \nNeural Computing and Applications  \n(2026) 38:25  \n[https://doi.org/10.1007/s00521-025-1](https://doi.org/10.1007/s00521-025-1)1737-x  \n1 3  \nCoP Coefficient of performance  \nCPU Central processing unit  \nDDPG Deep deterministic policy gradient  \nDL Deep learning  \nDMA Direct memory access  \nDRL Deep reinforcement learning  \nDSP Digital signal processing (block)  \nFastML-GA Fast machine learning with genetic algorithm FPGA Field-programmable gate array  \nGA Genetic algorithm  \nGA-Opt Genetic algorithm optimization  \nHLS High-level synthesis  \nHVAC Heating, ventilation, and air conditioning  \nII Initiation interval  \nIoT Internet of Things  \nMAE Mean absolute error  \nML Machine learning  \nMPC Model predictive control  \nPMV Predicted mean vote  \nRBFNN Radial basis function neural network  \nRF Random forest  \nRFR Random forest regressor  \nRH Relative humidity  \nRMSE Root mean square error  \nRT Room temperature  \nRTL Register transfer level  \nSEMS Smart energy management system  \nSoC System on chip  \nWT Water temperature  \n1 Introduction  \nThe building sector is a cornerstone of global decarbonisation strategies, accounting for approximately 34% of global final energy consumption and 37% of energy-related CO2 emissions as of 2022 [1] . Heating, ventilation, and air conditioning (HVAC) systems, which can consume up to 40% of a building’s total energy [2], represent a critical opportunity for improving energy efficiency and reducing e","cbCaibqVCUELTYk9","https://ap.wps.com/l/cbCaibqVCUELTYk9","pdf",6127244,1,31,"English","en",105,"# Abstract\n# Abbreviations\n# 1 Introduction\n## HVAC energy and decarbonisation context\n## Limitations of rule-based and static scheduling\n## ML-based predictive control and random forest surrogates\n## Challenges of CPU/cloud architectures for real-time deployment","[{\"question\":\"FastML-GA如何提升HVAC系统的实时能耗优化能力？\",\"answer\":\"通过混合部署：FPGA上实现随机森林代理模型加速推理，处理系统PS上运行轻量自适应遗传算法进行多目标优化，从而提升实时性与计算效率。\"},{\"question\":\"该框架在PYNQ-Z1 FPGA上取得了怎样的性能结果？\",\"answer\":\"实验表明可以达到超过1.67 million predictions per second，并且相较近期的FPGA方法具有显著优势。\"},{\"question\":\"FastML-GA如何在节能与舒适度之间进行权衡？\",\"answer\":\"采用GA多目标适应度函数动态优化逐小时送风量与送风温度，综合降低电能和热能消耗，并将舒适度维持在PMV阈值范围内。\"}]","FastML-GA - FPGA-accelerated machine learning for realtime energy HVAC optimization in buildings | PDF",1785811178,78,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"fastml-ga-fpga-accelerated-machine-learning-for-realtime-energy-hvac-optimization-in-buildings","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/fastml-ga-fpga-accelerated-machine-learning-for-realtime-energy-hvac-optimization-in-buildings/122540/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"FastML-GA如何提升HVAC系统的实时能耗优化能力？","Question",{"text":75,"@type":76},"通过混合部署：FPGA上实现随机森林代理模型加速推理，处理系统PS上运行轻量自适应遗传算法进行多目标优化，从而提升实时性与计算效率。","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"该框架在PYNQ-Z1 FPGA上取得了怎样的性能结果？",{"text":80,"@type":76},"实验表明可以达到超过1.67 million predictions per second，并且相较近期的FPGA方法具有显著优势。",{"name":82,"@type":73,"acceptedAnswer":83},"FastML-GA如何在节能与舒适度之间进行权衡？",{"text":84,"@type":76},"采用GA多目标适应度函数动态优化逐小时送风量与送风温度，综合降低电能和热能消耗，并将舒适度维持在PMV阈值范围内。","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]