{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Uncertainties Example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from IPython.display import display, HTML\n",
    "display(HTML('<a target=\"_blank\" href=\"https://colab.research.google.com/github/WaterFutures/EPyT-Flow/blob/main/docs/examples/uncertainties.ipynb\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>'))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This example demonstrates how apply uncertainties to model parameters such as demand patterns."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install epyt-flow --quiet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from epyt_flow.data.networks import load_ltown\n",
    "from epyt_flow.simulation import ScenarioSimulator, ModelUncertainty, \\\n",
    "    RelativeUniformUncertainty\n",
    "from epyt_flow.utils import to_seconds, plot_timeseries_data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Load the [L-Town network](https://epyt-flow.readthedocs.io/en/stable/epyt_flow.data.html#epyt_flow.data.networks.load_ltown) with realistic demands:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "network_config = load_ltown(include_default_sensor_placement=True,\n",
    "                            use_realistic_demands=True, verbose=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Create a new [simulation](https://epyt-flow.readthedocs.io/en/stable/epyt_flow.simulation.html#epyt_flow.simulation.scenario_simulator.ScenarioSimulator):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "sim = ScenarioSimulator(scenario_config=network_config)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Set simulation duration to two hours:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "sim.set_general_parameters(simulation_duration=to_seconds(hours=2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Add [uncertainty](https://epyt-flow.readthedocs.io/en/stable/tut.uncertainty.html) (i.e. randomness) with respect to the demand pattern -- i.e. demand pattern values can deviate up to 25% from their original value.\n",
    "Consequently, the simulation is no longer deterministic and the results vary from run to run.\n",
    "\n",
    "Here, we use [RelativeUniformUncertainty](https://epyt-flow.readthedocs.io/en/stable/epyt_flow.uncertainty.html#epyt_flow.uncertainty.uncertainties.RelativeUniformUncertainty) for the demand pattern uncertainty and set it by calling [set_model_uncertainty()](https://epyt-flow.readthedocs.io/en/stable/epyt_flow.simulation.html#epyt_flow.simulation.scenario_simulator.ScenarioSimulator.set_model_uncertainty):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "uc = RelativeUniformUncertainty(low=0.75, high=1.25)\n",
    "\n",
    "sim.set_model_uncertainty(ModelUncertainty(global_demand_pattern_uncertainty=uc))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Run simulation three times and retrieve sensor readings at node \"n105\" -- do not forget to set `reapply_uncertainties=True` to get reset the uncertainties before each simulation run:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "measurements = []\n",
    "for _ in range(3):\n",
    "    scada_data = sim.run_simulation(reapply_uncertainties=True)\n",
    "    measurements.append(scada_data.get_data_pressures(sensor_locations=[\"n105\"]).\n",
    "                        flatten().tolist())\n",
    "\n",
    "plot_timeseries_data(np.array(measurements),\n",
    "                     labels=[f\"Scenario {s_id}\" for s_id in range(len(measurements))],\n",
    "                     x_axis_label=\"Time (5min steps)\", y_axis_label=\"Pressure in $m$\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Do not forget to close the simulation!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "sim.close()"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.21"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}