SMDP-Based Dynamic Batching for Improving Responsiveness and Energy Efficiency of Batch Services

• URL: http://arxiv.org/abs/2501.02181v1
• Date: Sat, 04 Jan 2025 04:14:09 GMT
• Title: SMDP-Based Dynamic Batching for Improving Responsiveness and Energy Efficiency of Batch Services
• Authors: Yaodan Xu, Sheng Zhou, Zhisheng Niu,
• Abstract summary: Parallel computing resources exhibit heightened computational and energy efficiency when operating with larger batch sizes. In the realm of online services, the adoption of a larger batch size may lead to longer response times. This paper aims to provide a dynamic scheme that delicately balances latency and efficiency.
• Score: 12.600853777230185
• License:
• Abstract: For servers incorporating parallel computing resources, batching is a pivotal technique for providing efficient and economical services at scale. Parallel computing resources exhibit heightened computational and energy efficiency when operating with larger batch sizes. However, in the realm of online services, the adoption of a larger batch size may lead to longer response times. This paper aims to provide a dynamic batching scheme that delicately balances latency and efficiency. The system is modeled as a batch service queue with size-dependent service times. Then, the design of dynamic batching is formulated as a semi-Markov decision process (SMDP) problem, with the objective of minimizing the weighted sum of average response time and average power consumption. A method is proposed to derive an approximate optimal SMDP solution, representing the chosen dynamic batching policy. By introducing an abstract cost to reflect the impact of "tail" states, the space complexity and the time complexity of the procedure can decrease by 63.5% and 98%, respectively. Numerical results showcase the superiority of SMDP-based batching policies across various parameter setups. Additionally, the proposed scheme exhibits noteworthy flexibility in balancing power consumption and latency.

Related papers

• Optimizing Load Scheduling in Power Grids Using Reinforcement Learning and Markov Decision Processes [0.0]
  This paper proposes a reinforcement learning (RL) approach to address the challenges of dynamic load scheduling. Our results show that the RL-based method provides a robust and scalable solution for real-time load scheduling.
  arXiv  Detail & Related papers  (2024-10-23T09:16:22Z)
• Switchable Decision: Dynamic Neural Generation Networks [98.61113699324429]
  We propose a switchable decision to accelerate inference by dynamically assigning resources for each data instance. Our method benefits from less cost during inference while keeping the same accuracy.
  arXiv  Detail & Related papers  (2024-05-07T17:44:54Z)
• LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism [12.521026493432181]
  Existing large language models (LLMs) cannot efficiently serve variable-length requests in different phases. We propose a new parallelism paradigm, elastic sequence parallelism (ESP), to adapt to the variance between different requests and phases. LoongServe improves the maximum throughput by up to 3.85$times$ compared to the chunked prefill and 5.81$times$ compared to the prefill-decoding disaggregation.
  arXiv  Detail & Related papers  (2024-04-15T07:45:04Z)
• Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach [58.57026686186709]
  We introduce the Convolutional Transformer layer (ConvFormer) and propose a ConvFormer-based Super-Resolution network (CFSR) CFSR inherits the advantages of both convolution-based and transformer-based approaches. Experiments demonstrate that CFSR strikes an optimal balance between computational cost and performance.
  arXiv  Detail & Related papers  (2024-01-11T03:08:00Z)
• Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization [71.87335804334616]
  Federated learning (FL) is a promising paradigm to enable collaborative model training with decentralized data. The training process of Large Language Models (LLMs) generally incurs the update of significant parameters. This paper proposes an efficient partial prompt tuning approach to improve performance and efficiency simultaneously.
  arXiv  Detail & Related papers  (2023-10-23T16:37:59Z)
• A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading [62.34538208323411]
  We propose a multi-head ensemble multi-task learning (MEMTL) approach with a shared backbone and multiple prediction heads (PHs) MEMTL outperforms benchmark methods in both the inference accuracy and mean square error without requiring additional training data.
  arXiv  Detail & Related papers  (2023-09-02T11:01:16Z)
• SMDP-Based Dynamic Batching for Efficient Inference on GPU-Based Platforms [14.42787221783853]
  This paper aims to provide a dynamic graphics policy that strikes a balance between efficiency and latency. The proposed solution has notable flexibility in balancing power consumption and latency.
  arXiv  Detail & Related papers  (2023-01-30T13:19:16Z)
• Collaborative Intelligent Reflecting Surface Networks with Multi-Agent Reinforcement Learning [63.83425382922157]
  Intelligent reflecting surface (IRS) is envisioned to be widely applied in future wireless networks. In this paper, we investigate a multi-user communication system assisted by cooperative IRS devices with the capability of energy harvesting.
  arXiv  Detail & Related papers  (2022-03-26T20:37:14Z)
• MCDS: AI Augmented Workflow Scheduling in Mobile Edge Cloud Computing Systems [12.215537834860699]
  Recently proposed scheduling methods leverage the low response times of edge computing platforms to optimize application Quality of Service (QoS) We propose MCDS: Monte Carlo Learning using Deep Surrogate Models to efficiently schedule workflow applications in mobile edge-cloud computing systems.
  arXiv  Detail & Related papers  (2021-12-14T10:00:01Z)
• Reinforcement Learning on Computational Resource Allocation of Cloud-based Wireless Networks [22.06811314358283]
  Wireless networks used for Internet of Things (IoT) are expected to largely involve cloud-based computing and processing. In a cloud environment, dynamic computational resource allocation is essential to save energy while maintaining the performance of the processes. This paper models this dynamic computational resource allocation problem into a Markov Decision Process (MDP) and designs a model-based reinforcement-learning agent to optimise the dynamic resource allocation of the CPU usage. The results show that our agent rapidly converges to the optimal policy, stably performs in different settings, outperforms or at least equally performs compared to a baseline algorithm in energy savings for different scenarios.
  arXiv  Detail & Related papers  (2020-10-10T15:16:26Z)
• Joint Parameter-and-Bandwidth Allocation for Improving the Efficiency of Partitioned Edge Learning [73.82875010696849]
  Machine learning algorithms are deployed at the network edge for training artificial intelligence (AI) models. This paper focuses on the novel joint design of parameter (computation load) allocation and bandwidth allocation.
  arXiv  Detail & Related papers  (2020-03-10T05:52:15Z)

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.