TTN-VEGAPULS-Air-exporter/prometheus-alerts.yml

# Prometheus Alert Rules for VEGAPULS Air Sensors
#
# Installation:
# 1. Copy this file to /etc/prometheus/rules/vegapuls-alerts.yml
# 2. Add to prometheus.yml:
#    rule_files:
#      - /etc/prometheus/rules/vegapuls-alerts.yml
# 3. Reload Prometheus: systemctl reload prometheus

groups:
  - name: ttn_vegapuls_air_alerts
    interval: 60s
    rules:
      # === Exporter Health ===
      
      - alert: VEGAPULSExporterDown
        expr: up{job="vegapuls-air"} == 0
        for: 5m
        labels:
          severity: critical
          component: exporter
        annotations:
          summary: "VEGAPULS Air exporter is down"
          description: "The VEGAPULS Air Prometheus exporter has been down for more than 5 minutes. Check the service status."
          runbook: "Check systemctl status vegapuls-exporter and journalctl -u vegapuls-exporter"
      
      # === Device Online Status ===
      
      - alert: VEGAPULSSensorOffline
        expr: vegapulsair_device_online == 0
        for: 10m
        labels:
          severity: warning
          component: sensor
        annotations:
          summary: "VEGAPULS sensor {{ $labels.device_id }} is offline"
          description: "Sensor {{ $labels.device_id }} has not sent an uplink for more than 19 hours and is considered offline."
          runbook: "Check sensor battery, LoRaWAN coverage, and TTN Console for error messages"
      
      - alert: VEGAPULSSensorMissing
        expr: |
          (time() - vegapulsair_last_uplink_seconds_ago) > 86400
        for: 30m
        labels:
          severity: critical
          component: sensor
        annotations:
          summary: "VEGAPULS sensor {{ $labels.device_id }} missing for over 24h"
          description: "Sensor {{ $labels.device_id }} has not transmitted for over 24 hours. Last uplink: {{ $value | humanizeDuration }} ago."
          runbook: "Physical inspection required. Check sensor power and installation."
      
      # === Battery Monitoring ===
      
      - alert: VEGAPULSBatteryCritical
        expr: vegapulsair_battery_percent < 10
        for: 1h
        labels:
          severity: critical
          component: battery
        annotations:
          summary: "VEGAPULS sensor {{ $labels.device_id }} battery critically low"
          description: "Battery level at {{ $value }}%. Sensor will stop functioning soon. Immediate replacement required."
          runbook: "Schedule urgent battery replacement"
      
      - alert: VEGAPULSBatteryLow
        expr: vegapulsair_battery_percent < 20
        for: 6h
        labels:
          severity: warning
          component: battery
        annotations:
          summary: "VEGAPULS sensor {{ $labels.device_id }} battery low"
          description: "Battery level at {{ $value }}%. Plan battery replacement soon."
          runbook: "Schedule battery replacement within 2-4 weeks"
      
      - alert: VEGAPULSBatteryWarning
        expr: vegapulsair_battery_percent < 30
        for: 12h
        labels:
          severity: info
          component: battery
        annotations:
          summary: "VEGAPULS sensor {{ $labels.device_id }} battery below 30%"
          description: "Battery level at {{ $value }}%. Monitor and plan replacement."
          runbook: "Add to maintenance schedule for next quarter"
      
      # === Signal Quality ===
      
      - alert: VEGAPULSWeakSignal
        expr: vegapulsair_rssi_dbm < -120
        for: 1h
        labels:
          severity: warning
          component: network
        annotations:
          summary: "VEGAPULS sensor {{ $labels.device_id }} has weak signal"
          description: "RSSI is {{ $value }} dBm (very weak). May indicate coverage issues or antenna problems."
          runbook: "Check gateway coverage, sensor placement, and antenna connection"
      
      - alert: VEGAPULSPoorSNR
        expr: vegapulsair_snr_db < -15
        for: 1h
        labels:
          severity: warning
          component: network
        annotations:
          summary: "VEGAPULS sensor {{ $labels.device_id }} has poor SNR"
          description: "Signal-to-Noise Ratio is {{ $value }} dB. Signal quality is degraded."
          runbook: "Check for interference, gateway issues, or repositioning sensor"
      
      # === Temperature Monitoring ===
      
      - alert: VEGAPULSTemperatureExtreme
        expr: |
          vegapulsair_temperature_celsius > 60 or
          vegapulsair_temperature_celsius < -20
        for: 30m
        labels:
          severity: warning
          component: environment
        annotations:
          summary: "VEGAPULS sensor {{ $labels.device_id }} extreme temperature"
          description: "Temperature is {{ $value }}°C, outside normal operating range."
          runbook: "Check sensor location and environmental conditions"
      
      # === Data Quality ===
      
      - alert: VEGAPULSNoDataReceived
        expr: |
          rate(vegapulsair_exporter_requests_total[5m]) > 0 and
          vegapulsair_devices_total == 0
        for: 15m
        labels:
          severity: warning
          component: integration
        annotations:
          summary: "VEGAPULS exporter receiving no device data"
          description: "Exporter is running and being scraped, but no device data is available. Check MQTT connection and TTN configuration."
          runbook: "Check exporter logs, TTN Console live data, and MQTT credentials"
      
      - alert: VEGAPULSAllDevicesOffline
        expr: |
          vegapulsair_devices_total > 0 and
          vegapulsair_devices_online == 0
        for: 30m
        labels:
          severity: critical
          component: system
        annotations:
          summary: "All VEGAPULS sensors are offline"
          description: "{{ $value }} devices are registered but none are online. System-wide issue suspected."
          runbook: "Check TTN gateway status, network connectivity, and power supply"
      
      # === Performance Monitoring ===
      
      - alert: VEGAPULSHighScrapeRate
        expr: rate(vegapulsair_exporter_requests_total[5m]) > 2
        for: 10m
        labels:
          severity: info
          component: performance
        annotations:
          summary: "High scrape rate on VEGAPULS exporter"
          description: "Prometheus is scraping at {{ $value }} requests/second. Consider increasing scrape_interval."
          runbook: "Review Prometheus configuration and adjust scrape_interval if needed"

# === Recording Rules for Easier Querying ===

  - name: vegapuls_air_recording_rules
    interval: 60s
    rules:
      # Battery drain rate (percent per day)
      - record: vegapulsair_battery_drain_rate_percent_per_day
        expr: |
          rate(vegapulsair_battery_percent[7d]) * -86400
      
      # Average signal strength per device (7 day)
      - record: vegapulsair_rssi_avg_7d
        expr: |
          avg_over_time(vegapulsair_rssi_dbm[7d])
      
      # Uplink frequency (uplinks per day)
      - record: vegapulsair_uplink_frequency_per_day
        expr: |
          86400 / avg_over_time(vegapulsair_last_uplink_seconds_ago[7d])
      
      # Device availability percentage (24h)
      - record: vegapulsair_device_availability_percent_24h
        expr: |
          avg_over_time(vegapulsair_device_online[24h]) * 100

# === Usage Examples ===
#
# Query battery drain rate:
#   vegapulsair_battery_drain_rate_percent_per_day
#
# Query devices with availability < 95%:
#   vegapulsair_device_availability_percent_24h < 95
#
# Query average RSSI over 7 days:
#   vegapulsair_rssi_avg_7d
#
# Query uplink frequency:
#   vegapulsair_uplink_frequency_per_day