As Exascale computing becomes a reality, the energy needs of compute nodes in
cloud data centers will continue to grow. A common approach to reducing this
energy demand is to limit the power consumption of hardware components when
workloads are experiencing bottlenecks elsewhere in the system. However,
designing a resource controller capable of detecting and limiting power
consumption on-the-fly is a complex issue and can also adversely impact
application performance. In this paper, we explore the use of Reinforcement
Learning (RL) to design a power capping policy on cloud compute nodes using
observations on current power consumption and instantaneous application
performance (heartbeats). By leveraging the Argo Node Resource Management (NRM)
software stack in conjunction with the Intel Running Average Power Limit (RAPL)
hardware control mechanism, we design an agent to control the maximum supplied
power to processors without compromising on application performance. Employing
a Proximal Policy Optimization (PPO) agent to learn an optimal policy on a
mathematical model of the compute nodes, we demonstrate and evaluate using the
STREAM benchmark how a trained agent running on actual hardware can take
actions by balancing power consumption and application performance.

当 Exascale 计算成为现实时，云数据中心的计算节点能源需求将继续增长。在系统其他方面经历瓶颈时，降低硬件组件的功耗是减少能源需求的常见方法之一。然而，设计一个能够实时检测和限制功耗的资源控制器是一个复杂的问题，可能会对应用性能产生不利影响。本文中，我们探索使用强化学习（RL）设计云计算节点上的功耗限制策略，利用当前功耗和瞬时应用性能（心跳）的观测。通过将 Argo Node Resource Management（NRM）软件堆栈与 Intel Running Average Power Limit（RAPL）硬件控制机制相结合，设计一个代理程序来控制处理器的最大供电功率，而不会影响应用性能。利用 Proximal Policy Optimization（PPO）代理程序在计算节点的数学模型上学习最优策略，我们使用 STREAM 基准测试演示和评估了在实际硬件上运行的经过训练的代理程序如何通过平衡功耗和应用性能来采取行动。

数据中心计算节点功耗降低的性能感知增强学习方法

A Reinforcement Learning Approach for Performance-aware Reduction in  Power Consumption of Data Center Compute Nodes

UCI WorldTour races, the premier men's elite road cycling tour, are grueling
events that put riders' physical fitness and endurance to the test. The coaches
of Team Jumbo-Visma have long been responsible for predicting the energy needs
of each rider of the Dutch team for every race on the calendar. Those must be
estimated to ensure riders have the energy and resources necessary to maintain
a high level of performance throughout a race. This task, however, is both
time-consuming and challenging, as it requires precise estimates of race speed
and power output. Traditionally, the approach to predicting energy needs has
relied on coaches' judgement and experience, but this method has its
limitations and often leads to inaccurate predictions. In this paper, we
propose a new, more effective approach to predicting energy needs for cycling
races. By predicting the speed and power with regression models, we provide the
coaches with calorie needs estimate for each individual rider per stage
instantly. In addition, we compare methods to quantify uncertainty in
estimating the speed and power of Team Jumbo-Visma riders for cycling races.
The empirical analysis of the jackknife+, jackknife-minmax,
jackknife-minmax-after-bootstrap, CV+, CV-minmax, conformalized quantile
regression (CQR) and inductive conformal prediction (ICP) methods in conformal
prediction reveals all methods except minmax based methods achieve valid
prediction intervals while producing prediction intervals tight enough to be
used for decision making. Furthermore, methods computing prediction intervals
of fixed size produce significantly tighter intervals for low significance
value. Among the methods computing intervals of varying length across the input
space, namely the CQR and ICP methods, ICP computes tighter prediction
intervals at larger significance level.

运用回归模型，预测速度和功率以提供每位选手的热量需求估计，以此改进 UCI 世界巡回赛中车队教练对选手能量的估算，采用多种预测间隔的方法对预测模型进行比较且发现使用最小值和最大值计算模型的方法能有效产生紧密的预测间隔。

团队 Jumbo-Visma 卡路里预测中的共形回归

Conformal Regression in Calorie Prediction for Team Jumbo-Visma

We introduce a DNN training technique that learns only a fraction of the full
parameter set without incurring an accuracy penalty. To do this, our algorithm
constrains the total number of weights updated during backpropagation to those
with the highest total gradients. The remaining weights are not tracked, and
their initial value is regenerated at every access to avoid storing them in
memory. This can dramatically reduce the number of off-chip memory accesses
during both training and inference, a key component of the energy needs of DNN
accelerators. By ensuring that the total weight diffusion remains close to that
of baseline unpruned SGD, networks pruned using our technique are able to
retain state-of-the-art accuracy across network architectures -- including
networks previously identified as difficult to compress, such as Densenet and
WRN. With ResNet18 on ImageNet, we observe an 11.7$\times$ weight reduction
with no accuracy loss, and up to 24.4$\times$ with a small accuracy impact.

本研究提出了一种 DNN 训练技术，该技术可以在不影响准确率的情况下，只学习了部分全参数集。此方法使用反向传播约束更新权重的总数，以仅跟踪具有最高总梯度的权重。通过确保总权重扩散保持接近于基线未修剪 SGD 的扩散，使用我们技术进行修剪的网络能够在网络架构中保留领先的状态，包括先前被认为难以压缩的网络。我们在 ImageNet 上使用 ResNet18 观察到了 11.7 倍的权重减少无准确性损失，最多可达 24.4 倍，但具有小的准确性影响。