From bdf0221fb8d508ecb5c3cfceadd035e343927ab1 Mon Sep 17 00:00:00 2001
From: John-Paul Robinson <jpr@uab.edu>
Date: Fri, 10 Jul 2020 17:02:35 -0500
Subject: [PATCH] Add notebook for generating power reports
---
power-stats.ipynb | 267 ++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 267 insertions(+)
create mode 100644 power-stats.ipynb
diff --git a/power-stats.ipynb b/power-stats.ipynb
new file mode 100644
index 0000000..4be3700
--- /dev/null
+++ b/power-stats.ipynb
@@ -0,0 +1,267 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Power Stats \n",
+ "\n",
+ "Use RestAPI to read power consumption info for cluster nodes and generate usage reports. this is based on the [pandas time series tutorial by Jennifer Walker](https://www.dataquest.io/blog/tutorial-time-series-analysis-with-pandas/)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import requests\n",
+ "import pprint\n",
+ "import datetime\n",
+ "import os\n",
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "import seaborn as sns\n",
+ "import matplotlib.pyplot as plt\n",
+ "import matplotlib.dates as mdates"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Set up credentials to query RestAPI. Bright controls access based on the user identity. The user's cert.pem and cert.key are automatically generated but the cacert.pem needs to be constructed from the certs returned by the master."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "cert_file='~/.cm/cert.pem'\n",
+ "key_file='~/.cm/cert.key'\n",
+ "ca_file='cacert.pem'"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "cert=(os.path.expanduser(cert_file), os.path.expanduser(key_file))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Gather Cluster Power Data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "startdate = '2020/01/01 00:00:00'\n",
+ "enddate = '2020/07/10 00:00:00'"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "params = (\n",
+ " ('start', startdate),\n",
+ " ('measurable', 'Pwr_Consumption'),\n",
+ " ('indent', '1'),\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "response = requests.get('https://master:8081/rest/v1/monitoring/dump', params=params, cert=cert, verify=ca_file)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Simply read the json response into a dataframe for futher parsing."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df = pd.DataFrame(response.json()[\"data\"])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Some of data values report unrealistic power values. Any reading over 10kW is considered invalid."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df = df.loc[df['raw'] < 10000]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Create a datatime type column from the reported sample times."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df['datetime'] = pd.to_datetime(df.time, format=\"%Y/%m/%d %H:%M:%S\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Create an index for the hourly "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "hourly_idx=pd.date_range(startdate, enddate, freq='H')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "debug=False\n",
+ "\n",
+ "# prepare data frame to append to, use zeros for default column \n",
+ "m6_hourly_pwr=pd.DataFrame(np.zeros((1,len(hourly_idx))).T, index=hourly_idx, columns=['sum'])\n",
+ "\n",
+ "for num, entity in enumerate(df.entity.unique()):\n",
+ " if entity not in ['c0108', 'c0009']:\n",
+ " node_pwr=df[df.entity==entity].set_index(\"datetime\")\n",
+ " node_pwr=node_pwr[['raw']].resample('H').mean()\n",
+ " node_pwr=node_pwr[startdate:enddate].fillna(method=\"ffill\")\n",
+ " if debug:\n",
+ " print(node_pwr)\n",
+ " missing = node_pwr['raw'].isnull().sum()\n",
+ " print(\"{}: {} missing {}\\n\".format(num, entity, missing))\n",
+ " m6_hourly_pwr[entity]= node_pwr[startdate:enddate]\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Plot Power Usage Graph\n",
+ "\n",
+ "\n",
+ "Pick the start and end date for the plots from the data range selected above. Generate the sum and plot only it's values.\n",
+ "\n",
+ "We skip over the first month of collection because it is uncommonly noisy."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "kW = m6_hourly_pwr['2020-02-01':'2020-07-09'].sum(axis=1)/1000"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "ax = kW.plot()\n",
+ "ax.set_ylabel(\"Power (kW)\")\n",
+ "ax.set_title(\"Cheaha compute and login node hourly power use\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Resample hourly sum to support the seven day average."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "kW_d = kW.resample('D').mean()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Compute the centered 7-day rolling mean\n",
+ "# https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.rolling.html\n",
+ "kW_7d = kW_d.rolling(7, center=True).mean()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Plot houry, daily, 7-day rolling mean\n",
+ "fig, ax = plt.subplots()\n",
+ "ax.plot(kW, marker='.', markersize=2, color='gray', linestyle='None', label='Hourly Average')\n",
+ "ax.plot(kW_d, color='brown', linewidth=2, label='1-day Average')\n",
+ "ax.plot(kW_7d, color='black', linewidth=4, label='7-day Rolling Average')\n",
+ "label='Trend (7 day Rolling Mean)'\n",
+ "ax.legend()\n",
+ "ax.set_ylabel('Power (kW)')\n",
+ "ax.set_title('Cheaha Trends in Electricity Consumption');"
+ ]
+ }
+ ],
+ "metadata": {
+ "language_info": {
+ "name": "python",
+ "pygments_lexer": "ipython3"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
--
GitLab