On the Effectiveness of Microservices Tactics and Patterns to Reduce Energy Consumption: An Experimental Study on Trade-Offs

• URL: http://arxiv.org/abs/2501.14402v1
• Date: Fri, 24 Jan 2025 11:15:23 GMT
• Title: On the Effectiveness of Microservices Tactics and Patterns to Reduce Energy Consumption: An Experimental Study on Trade-Offs
• Abstract summary: Microservice-based systems have established themselves in the software industry.<n> sustainability-related legislation and the growing costs of energy-hungry software increase the importance of energy efficiency for these systems.<n>While some proposals for architectural tactics and patterns exist, their effectiveness as well as potential trade-offs on other quality attributes (QAs) remain unclear.
• Score: 3.928499292698212
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Context: Microservice-based systems have established themselves in the software industry. However, sustainability-related legislation and the growing costs of energy-hungry software increase the importance of energy efficiency for these systems. While some proposals for architectural tactics and patterns exist, their effectiveness as well as potential trade-offs on other quality attributes (QAs) remain unclear. Goal: We therefore aim to study the effectiveness of microservices tactics and patterns to reduce energy consumption, as well as potential trade-offs with performance and maintainability. Method: Using the open-source Online Boutique system, we conducted a controlled experiment with three tactics and three patterns, and analyzed the impact of each technique compared to a baseline. We also tested with three levels of simulated request loads (low, medium, high). Results: Request load moderated the effectiveness of reducing energy consumption. All techniques (tactics and patterns) reduced the energy consumption for at least one load level, up to 5.6%. For performance, the techniques could negatively impact response time by increasing it by up to 25.9%, while some also decreased it by up to 72.5%. Two techniques increased the throughput, by 1.9% and 34.0%. For maintainability, three techniques had a negative, one a positive, and two no impact. Conclusion: Some techniques reduced energy consumption while also improving performance. However, these techniques usually involved a trade-off in maintainability, e.g., via more code duplication and module coupling. Overall, all techniques significantly reduced energy consumption at higher loads, but most of them sacrificed one of the other QAs. This highlights that the real challenge is not simply reducing energy consumption of microservices, but to achieve energy efficiency.

Related papers

• From Perception to Action: Can UI Interventions Foster Sustainable LLM Chatbot [2.930725408634743]
  This study investigates whether sustainability-oriented user-interface interventions can increase users' energy awareness and encourage more energy-responsible use.<n>We implemented a prototype with a three-mode switch (Energy-efficient, Balanced, Performance), per-response energy feedback, pre-send energy estimates, a usage metrics dashboard, and energy analogies.<n>In the baseline survey, 94.8% of respondents reported at least some awareness of AI energy use, yet 88.3% misestimated actual consumption.<n>Although concern about environmental impact was high, only 39.0% indicated willingness to accept a performance trade-off for lower energy use.
  arXiv  Detail & Related papers  (2026-06-09T13:39:21Z)
• Towards Green AI: Decoding the Energy of LLM Inference in Software Development [46.879983975894135]
  AI-assisted tools are increasingly integrated into software development, but their reliance on large language models (LLMs) introduces substantial computational and energy costs.<n>We conduct a phase-level analysis of LLM inference energy consumption, distinguishing between the (1) prefill, where the model processes the input and builds internal representations, and (2) decoding, where output tokens are generated using the stored state.
  arXiv  Detail & Related papers  (2026-02-05T14:38:19Z)
• Reducing Compute Waste in LLMs through Kernel-Level DVFS [0.4747334911695324]
  We propose a kernel-level, DVFS approach that explores new frequency configurations, and prove these save more energy than previous, pass- or iteration-level solutions.<n>For a GPT-3 training run, a pass-level approach could reduce energy consumption by 2% (without losing performance), while our kernel-level approach saves as much as 14.6%.
  arXiv  Detail & Related papers  (2026-01-13T13:26:57Z)
• On the Effectiveness of Proposed Techniques to Reduce Energy Consumption in RAG Systems: A Controlled Experiment [2.7757571644758166]
  This study presents a controlled experiment investigating five practical techniques aimed at reducing energy consumption in RAG systems.<n>We evaluated the impact of these techniques on energy consumption, latency, and accuracy.<n>We reveal that techniques such as increasing similarity retrieval thresholds, reducing embedding sizes, applying vector indexing, and using a BM25S reranker can significantly reduce energy usage, up to 60% in some cases.
  arXiv  Detail & Related papers  (2026-01-05T19:50:49Z)
• Green LLM Techniques in Action: How Effective Are Existing Techniques for Improving the Energy Efficiency of LLM-Based Applications in Industry? [2.3683790724077864]
  The rapid adoption of large language models (LLMs) has raised concerns about their substantial energy consumption.<n>We analyzed an application in an industrial context at Schuberg Philis, a Dutch IT services company.<n>Several techniques, such as Prompt Optimization and 2-bit Quantization, managed to reduce energy use significantly, sometimes by up to 90%.<n>The only technique that achieved significant and strong energy reductions without harming the other qualities substantially was Small and Large Model Collaboration via Nvidia's Prompt Task and Complexity.
  arXiv  Detail & Related papers  (2026-01-05T19:35:29Z)
• METRION: A Framework for Accurate Software Energy Measurement [0.509780930114934]
  Information and Communication Technology sector accounted for 1.4% of global greenhouse gas emissions in 2020.<n>To reduce this environmental impact, optimization strategies are employed to reduce energy consumption at the IT infrastructure and application levels.<n>We introduce an energy attribution model that quantifies the energy consumption of applications on CPU and DRAM at the thread level.
  arXiv  Detail & Related papers  (2025-12-07T11:45:16Z)
• EfficientLLM: Efficiency in Large Language Models [64.3537131208038]
  Large Language Models (LLMs) have driven significant progress, yet their growing counts and context windows incur prohibitive compute, energy, and monetary costs.<n>We introduce EfficientLLM, a novel benchmark and the first comprehensive empirical study evaluating efficiency techniques for LLMs at scale.
  arXiv  Detail & Related papers  (2025-05-20T02:27:08Z)
• Evaluating energy inefficiency in energy-poor households in India: A frontier analysis approach [0.0]
  Energy-poor households often compromise their thermal comfort and refrain from operating mechanical cooling devices. Due to a lack of comprehensive data in India, little is understood about their electricity consumption patterns and usage efficiency. This study measures the inefficiency in electricity consumption due to 91% household practices and appliances in social housing in Mumbai, India.
  arXiv  Detail & Related papers  (2025-04-23T19:05:07Z)
• The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking [72.45765726160151]
  This work identifies the Energy Loss Phenomenon in Reinforcement Learning from Human Feedback and its connection to reward hacking. We propose an Energy loss-aware PPO algorithm (EPPO) which penalizes the increase in energy loss in the final layer during reward calculation to prevent excessive energy loss.
  arXiv  Detail & Related papers  (2025-01-31T18:10:53Z)
• From Efficiency Gains to Rebound Effects: The Problem of Jevons' Paradox in AI's Polarized Environmental Debate [69.05573887799203]
  Much of this debate has concentrated on direct impact without addressing the significant indirect effects. This paper examines how the problem of Jevons' Paradox applies to AI, whereby efficiency gains may paradoxically spur increased consumption. We argue that understanding these second-order impacts requires an interdisciplinary approach, combining lifecycle assessments with socio-economic analyses.
  arXiv  Detail & Related papers  (2025-01-27T22:45:06Z)
• Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracy [3.6731536660959985]
  Deep learning models in computer vision pose increasing concerns about energy consumption and sustainability.<n>We conduct a comprehensive analysis of the inference energy consumption of 1,200 ImageNet classification models.<n>We identify key factors contributing to energy consumption and demonstrate methods to improve energy efficiency.
  arXiv  Detail & Related papers  (2024-12-12T21:44:08Z)
• Just In Time Transformers [2.7350304370706797]
  JITtrans is a novel transformer deep learning model that significantly improves energy consumption forecasting accuracy. Our findings highlight the potential of advanced predictive technologies to revolutionize energy management and advance sustainable power systems.
  arXiv  Detail & Related papers  (2024-10-22T10:33:00Z)
• A Safe Genetic Algorithm Approach for Energy Efficient Federated Learning in Wireless Communication Networks [53.561797148529664]
  Federated Learning (FL) has emerged as a decentralized technique, where contrary to traditional centralized approaches, devices perform a model training in a collaborative manner. Despite the existing efforts made in FL, its environmental impact is still under investigation, since several critical challenges regarding its applicability to wireless networks have been identified. The current work proposes a Genetic Algorithm (GA) approach, targeting the minimization of both the overall energy consumption of an FL process and any unnecessary resource utilization.
  arXiv  Detail & Related papers  (2023-06-25T13:10:38Z)
• Compute and Energy Consumption Trends in Deep Learning Inference [67.32875669386488]
  We study relevant models in the areas of computer vision and natural language processing. For a sustained increase in performance we see a much softer growth in energy consumption than previously anticipated.
  arXiv  Detail & Related papers  (2021-09-12T09:40:18Z)
• Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision [31.781943982148025]
  We present the first large-scale energy consumption benchmark for efficient computer vision models. A new metric is proposed to explicitly evaluate the full-cycle energy consumption under different model usage intensity.
  arXiv  Detail & Related papers  (2021-08-30T18:22:36Z)
• ECO: Enabling Energy-Neutral IoT Devices through Runtime Allocation of Harvested Energy [0.8774604259603302]
  We present a runtime-based energy-allocation framework to optimize the utility of the target device under energy constraints. The proposed framework uses an efficient iterative algorithm to compute initial energy allocations at the beginning of a day. We evaluate this framework using solar and motion energy harvesting modalities and American Time Use Survey data from 4772 different users.
  arXiv  Detail & Related papers  (2021-02-26T17:21:25Z)
• Risk-Aware Energy Scheduling for Edge Computing with Microgrid: A Multi-Agent Deep Reinforcement Learning Approach [82.6692222294594]
  We study a risk-aware energy scheduling problem for a microgrid-powered MEC network. We derive the solution by applying a multi-agent deep reinforcement learning (MADRL)-based advantage actor-critic (A3C) algorithm with shared neural networks.
  arXiv  Detail & Related papers  (2020-02-21T02:14:38Z)
• Multi-Agent Meta-Reinforcement Learning for Self-Powered and Sustainable Edge Computing Systems [87.4519172058185]
  An effective energy dispatch mechanism for self-powered wireless networks with edge computing capabilities is studied. A novel multi-agent meta-reinforcement learning (MAMRL) framework is proposed to solve the formulated problem. Experimental results show that the proposed MAMRL model can reduce up to 11% non-renewable energy usage and by 22.4% the energy cost.
  arXiv  Detail & Related papers  (2020-02-20T04:58:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.