计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (5): 376-387.doi: 10.11896/jsjkx.250300140

• 计算机体系结构 • 上一篇    下一篇

面向异构智能储算能效优化的改进河马算法

王恩良1,2, 夏郡2,3, 孙知信2,3   

  1. 1 南京邮电大学物联网学院 南京 210003
    2 南京邮电大学国家邮政局邮政行业技术研发中心(物联网技术) 南京 210003
    3 南京邮电大学江苏省邮政大数据技术与应用工程研究中心 南京 210003
  • 收稿日期:2025-03-26 修回日期:2025-06-16 发布日期:2026-05-08
  • 通讯作者: 孙知信(sunzx@niupt.edu.cn)
  • 作者简介:(3386204603@qq.com)
  • 基金资助:
    国家自然科学基金(61972208,62272239);江苏省农业科技创新基金(JASTIF)(CX(22)1007)

Improved Hippopotamus Algorithm for Energy Efficiency Optimization of HeterogeneousIntelligent Storage Computing

WANG Enliang1,2, XIA Jun2,3, SUN Zhixin2,3   

  1. 1 School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
    2 Postal Industry Technology Research and Development Center of National Post Bureau(Internet of Things Technology), Nanjing University of Posts and Telecommunications, Nanjing 210003, China
    3 Post Big Data Technology and Application Engineering Research Center of Jiangsu Province, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
  • Received:2025-03-26 Revised:2025-06-16 Online:2026-05-08
  • About author:WANG Enliang,born in 1998,Ph.D candidate.His main research interests include high performance computing,optimization algorithms and deep lear-ning.
    SUN Zhixin,born in 1964,Ph.D,professor,doctoral supervisor.His main research interests include the theory and technology of network communication,computer network and security.
  • Supported by:
    National Natural Science Foundation of China(61972208,62272239) and Jiangsu Agriculture Science and Technology Innovation Fund(JASTIF)(CX(22)1007).

PDF (PC)

228

摘要： 数据中心的高能耗问题在数字化转型与"双碳"战略背景下日益凸显,其根源在于传统分布式架构中频繁的数据传输引发的能效瓶颈。现有优化方法局限于单一维度(如任务调度或存储层级优化),难以协同适配动态负载与异构资源环境。对此,提出一种基于改进河马优化算法(IHOA)的智能储算系统能效优化框架,通过构建计算、存储与通信能耗的多维度统一模型,将任务分配与数据放置联合优化。该框架创新性地引入储算协同感知机制,量化任务与数据的关联性,并结合能效敏感的适应性搜索策略,动态调整局部与全局搜索强度,以适配异构设备的能效特性。实验结果表明,相较于主流优化算法,IHOA在中等至大规模系统中显著降低了总能耗,能效提升幅度为8.1%~25.6%,其优势源于对远程数据传输能耗的高效抑制与异构资源的动态适配。能耗构成分析进一步验证了IHOA在全局协同优化中的有效性,其通过减少跨节点数据迁移,使数据传输能耗降低17%~32%。这为智能储算系统的绿色化设计提供了理论支持与技术路径,推动数据中心向高效、低碳方向演进,并为边缘计算等新兴场景的能效优化提供了方法论参考。

关键词: 智能储算系统, 能效优化, 改进河马优化算法, 异构计算, 可持续计算

Abstract: The high energy consumption issue in data centers has become increasingly prominent amid digital transformation and the “dual carbon” strategy,stemming from energy efficiency bottlenecks caused by frequent data transmission in traditional distributed architectures.Existing optimization methods are confined to single dimensions(such as task scheduling or storage hierarchy optimization),struggling to collaboratively adapt to dynamic workloads and heterogeneous resource environments.This paper proposes an energy efficiency optimization framework for intelligent storage-computing systems based on the improved hippopo-tamus optimization algorithm(IHOA),which jointly optimizes task allocation and data placement through a multi-dimensional unified model encompassing computation,storage,and communication energy consumption.The framework innovatively introduces a storage-computing collaborative awareness mechanism that quantifies task-data correlations,combined with energy-efficiency-sensitive adaptive search strategies that dynamically adjust local and global search intensities to accommodate the energy efficiency characteristics of heterogeneous devices.Experimental results demonstrate that compared to mainstream optimization algorithms,IHOA significantly reduces total energy consumption in medium to large-scale systems,with efficiency improvements ranging from 8.1% to 25.6%,deriving its advantages from efficient suppression of remote data transmission energy consumption and dynamic adaptation to heterogeneous resources.Energy composition analysis further validates IHOA’s effectiveness in global collaborative optimization,achieving 17%~32% reduction in data transmission energy consumption by minimizing cross-node data migration.This research provides theoretical support and technical pathways for the green design of intelligent storage-computing systems,driving data centers toward high-efficiency,low-carbon development,while offering methodological references for energy efficiency optimization in emerging scenarios such as edge computing.

Key words: Intelligent storage and computing system, Energy efficiency optimization, Improved hippopotamus optimization algorithm, Heterogeneous computing, Sustainable computing

中图分类号: 

  • TP311.5
[1]LUO D,LI Y X.Analysis of the current statusof data center ener-gy consumption and exploration of green development[J].Communications World,2022(17):36-38.
[2]CAI Z,CHEN Z,CHEN X,et al.SPSC:Stream processingframework atop serverless computing for industrial big data[J].IEEE Transactions on Cybernetics,2024,54(11):6509-6517.
[3]ORGERIE A C,ASSUNCAO M D,LEFEVRE L.A survey on techniques for improving the energy efficiency of large-scale distributed systems[J].ACM Computing Surveys,2014,46(4):1-31.
[4]WANG J,LI X,RUIZ R,et al.Energy utilization task scheduling for mapreduce in heterogeneous clusters[J].IEEE Transactions on Services Computing,2020,15(2):931-944.
[5]DAYARATHNA M,WEN Y,FAN R.Data center energy consumption modeling:A survey[J].IEEE Communications Surveys &Tutorials,2015,18(1):732-794.
[6]SHEHABI A,SMITH S,SARTOR D,et al.United states data center energy usage report:LBNL-1005775[R].Berkeley,CA:Lawrence Berkeley National Laboratory,2016.
[7]BARROSO L A,HÖLZLE U,RANGANATHAN P.The datacenter as a computer:Designing warehouse-scale machines[M].Springer Nature,2019.
[8]LÜTTGAU J,KUHN M,DUWE K,et al.Survey of storagesystems for high-performance computing[J].Supercomputing Frontiers and Innovations,2018,5(1):31-58.
[9]ZHANG Y,LIU M,WANG H,et al.Research on WebAssembly Runtimes:A Survey[J].ACM Transactions on Software Engineering and Methodology,2024,34(8):1-47.
[10]BELLOUM D D A.Evaluating Energy Consumption of Distri-buted and Non-Distributed File Systems[D].Amsterdam:University of Amsterdam and Vrije Universiteit Amsterdam,2019.
[11]GILL S S,XU M,OTTAVIANI C,et al.AI for next generation computing:Emerging trends and future directions[J].Internet of Things,2022,19:100514.
[12]LO D,CHENG L,GOVINDARAJU R,et al.Heracles:Improving resource efficiency at scale[C]//Proceedings of the 42nd Annual International Symposium on Computer Architecture.2015:450-462.
[13]YU B,PAN J.Location-aware associated data placement forgeo-distributed data-intensive applications[C]//2015 IEEE Conference on Computer Communications(INFOCOM).IEEE,2015:603-611.
[14]ZAHARIA M,CHOWDHURY M,DAS T,et al.Resilient distributed datasets:A {Fault-Tolerant} abstraction for {In-Me-mory} cluster computing[C]//9th USENIX Symposium on Networked Systems Design and Implementation(NSDI 12).2012:15-28.
[15]LI Z,CHENG J,CHEN Q,et al.{RunD}:A lightweight secure container runtime for high-density deployment and high-concurrency startup in serverless computing[C]//2022 USENIX Annual Technical Conference(USENIX ATC 22).2022:53-68.
[16]SMITH M,ZHAO L,CORDOVA J,et al.Machine Learning-Based Energy-efficient Workload Management for Data Centers[C]//2024 IEEE 21st Consumer Communications & Networking Conference(CCNC).IEEE,2024:799-802.
[17]MAYER R,SLO A,TARIQ M A,et al.SPECTRE:Supporting consumption policies in window-based parallel complex event processing[C]//Proceedings of the 18th ACM/IFIP/USENIX Middleware Conference.2017:161-173.
[18]LI R,ZHOU Z,ZHANG X,et al.Joint application placement and request routing optimization for dynamic edge computing service management[J].IEEE Transactions on Parallel and Distributed Systems,2022,33(12):4581-4596.
[19]QASAIMEH M,DENOLF K,LO J,et al.Comparing energy efficiency of CPU,GPU and FPGA implementations for vision kernels[C]//2019 IEEE International Conference on Embedded Software and Systems(ICESS).IEEE,2019:1-8.
[20]FOWERS J,BROWN G,COOKE P,et al.A performance and energy comparison of FPGAs,GPUs,and multicores for sliding-window applications[C]//Proceedings of the ACM/SIGDA International Symposium on Field Programmable Gate Arrays.2012:47-56.
[21]FAN H,XU G P,XUE Y B,et al.An Energy Consumption Optimization and Evaluation for Hybrid Cache Based on Reinforcement Learning[J].Journal of Computer Research and Development,2020,57(6):1125-1139.
[22]ZENG Q,DU Y,HUANG K,et al.Energy-efficient resource management for federated edge learning with CPU-GPU heterogeneous computing[J].IEEE Transactions on Wireless Communications,2021,20(12):7947-7962.
[23]GEORGIOS C,EVANGELIA F,CHRISTOS M,et al.Exploring cost-efficient bundling in a multi-cloud environment[J].Simulation Modelling Practice and Theory,2021,111:102338.
[24]MAO Y Y,SHI E Y,JIANG C F,et al.Data center energy efficiency simulation based on genetic algorithm[J].Computer Engineering & Science,2021,43(8):1341-1352.
[25]AMIRI M H,MEHRABI HASHJIN N,MONTAZERI M,et al.Hippopotamus optimization algorithm:a novel nature-inspired optimization algorithm[J].Scientific Reports,2024,14(1):5032.
[26]QIN X,LONG W.An Improved whale optimization algorithm based on stochastic differential mutation[J].China Sciencepaper,2018,13(8):937-942.
[27]QU C,HE W,PENG X,et al.Harris hawks optimization with information exchange[J].Applied Mathematical Modelling,2020,84:52-75.
[28]MA J,HAO Z,SUN W.Enhancing sparrow search algorithm via multi-strategies for continuous optimization problems[J].Information Processing & Management,2022,59(2):102854.
[29]YU P.Improved Grasshopper Optimization Algorithm Combi-ning Improved DBSCAN Clustering and Multiple Evolutionary Strategie[J].Instrument Technique and Sensor,2024(5):98-105,112.
[30]CUONG-LE T,MINH H L,KHATIR S,et al.A novel version of Cuckoo search algorithm for solving optimization problems[J].Expert Systems with Applications,2021,186:115669.
[31]DENG Y,LIU Z,WU Y.Topology optimization of capillary,two-phase flow problems[J].Communications in Computational Physics,2017,22(5):1413-1438.
[32]SHADRAVAN S,NAJI H R,BARDSIRI V K.The Sailfish Optimizer:A novel nature-inspired metaheuristic algorithm for solving constrained engineering optimization problems[J].Engineering Applications of Artificial Intelligence,2019,80:20-34.
[33]WANG J Y,ZHOU B Y,ZHANG F,et al.Data Center Energy Consumption Models and Energy Efficient Algorithms[J].Journal of Computer Research and Development,2019,56(8):1587-1603.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发