Database Anomaly Detection Powered by Machine Learning

Improve database performance by using an anomaly detection tool

Automatically learn about database wait behavior patterns using an anomaly detection tool

Automatically learn about database wait behavior patterns using an anomaly detection tool

When you rely on tribal knowledge, it’s hard for someone new to acquire it. Sometimes, the sheer scale in larger environments prohibits in-depth, broad understanding. Remove the need for tribal knowledge and let the machine learning algorithm in SolarWinds® Database Performance Analyzer (DPA) help automate the “understanding” of normal behavior patterns. Don’t let knowledge walk out the door when a key resource moves on; automate and retain the knowledge to benefit everyone on your team.

The machine learning algorithm in DPA is designed to get smarter over time and improves its predictive accuracy as more data is collected.

Dig deeper into anomaly-based database monitoring by going beyond spikes

Dig deeper into anomaly-based database monitoring by going beyond spikes

Database administrators tend to focus on spikes in database performance. While this can be a good way to zero in on problem behavior, analyzing behavior spikes isn’t the only indicator of performance changes. In fact, performance variability is normal in most production databases and should be expected. Database administrators need a way to account for expected variations and call out anything unexpected.

The smart SQL database anomaly detection in DPA can go beyond spikes to account for expected variations and point out when something unexpected happens. This anomaly detection tool highlights such occurrences, giving you multiple ways to know when things deviate from the norm.

Troubleshoot effectively using an anomaly detection tool designed to alert on significant behavioral changes

Troubleshoot effectively using an anomaly detection tool designed to alert on significant behavioral changes

Detecting database anomalies is one thing, but since no one stares at a dashboard 24/7, DPA can send alerts when behavior changes are detected. Reduce noise by customizing the sensitivity to a level you’re comfortable with and let DPA do the watching for you.

DPA constantly monitors your database and can send alerts when behavior changes are detected. This anomaly detection tool can let you know when the workload shifts, when maintenance jobs run into business hours, or when other unexpected changes you want to investigate occur.

Leverage the most recent data available for SQL database anomaly detection

Leverage the most recent data available for SQL database anomaly detection

A database anomaly detection tool is only as good as the data going into it. DPA offers 24/7, down-to-the-minute anomaly-based monitoring, with a machine learning algorithm designed to offer updated insights. If monitoring stops for more than 30 days, DPA’s algorithm won’t make predictions on stale data. Instead, DPA starts learning from new data, and after three days, it starts making predictions again based on the most current data. This feature helps ensure your anomaly detection efforts are backed by only the most recent, relevant data.

Use a robust anomaly detection tool compatible with multiple database types

Use a robust anomaly detection tool compatible with multiple database types

As environments become larger and more complex, database administrators need an anomaly detection tool capable of monitoring a wide variety of database types. Database Performance Analyzer offers an anomaly-based database monitoring tool for virtualized, physical, and cloud-based database instances on Windows and Linux servers, in Azure, or as an AWS subscription using one installation. The DPA anomaly detection tool is built to support Oracle, MySQL, Azure SQL Database, Microsoft SQL Server, and more. DPA also features integrated VMware ESXi visualization with VM option.
Get More on Anomaly Detection Tools
Do you find yourself asking…
  • Why should I use anomaly detection in database monitoring?
  • How does machine learning help with anomaly detection?
  • How does anomaly-based database monitoring work in DPA?

  • Why should I use anomaly detection in database monitoring?

    Anomaly detection in a database, usually powered by machine learning, is a method of identifying unusual events in a database. Though databases can have outliers (and anomalies are outliers in most cases), not all outliers are anomalies. An anomaly detection tool can help DBAs more easily find “unusual” or “unexpected” instances based on database performance baselines, defining unusual and unexpected as “statistically improbable.”

    Anomaly detection in database monitoring is ideal for the following:

    • Finding unusual metric values to identify undetected issues
    • Finding changes in important metrics for database administrators to investigate
    • Zeroing in on where to search when trying to diagnose a detected problem 
    • Reducing the need to recalibrate thresholds

    DBAs can use anomaly detection in database monitoring to help drill down into what matters more quickly. A database anomaly detection tool can also alert DBAs to unusual changes potentially indicating a database performance problem before it grows into a bottleneck.

  • How does machine learning help with anomaly detection?

    Machine learning helps improve anomaly detection in a couple key areas:

    • Increases Accuracy: Machine learning makes anomaly-based monitoring for databases more accurate. To effectively highlight unusual events in your database, the anomaly detection tool must first establish a baseline of your database performance. However, these baselines change over time as you reoptimize and table tune. Machine learning can automatically account for these changes, recalibrate, and create new baselines, so DBAs have the most accurate data to work with. Also, machine learning can make the anomaly detection tool smarter over time, so its alerts become more accurate. 

    • Reduces Complexity: Machine learning uses automation and fast analysis to help database administrators break down large data sets so they can use them to create actionable tasks. It also helps reduce complexity in troubleshooting, as machine learning can point DBAs to where performance issues may be. This makes it so they don’t have to search the entire database for them. 

  • How does anomaly-based database monitoring work in DPA?

    Anomaly-based database monitoring in SolarWinds® Database Performance Analyzer (DPA) is built to help inform performance optimization efforts in two major ways:

    1. The machine learning algorithm learns what “normal” is for your database and predicts wait times. The algorithm requires a minimum of three days of data to start “learning” and can use up to 90 days of historical learning. DPA collects the data from the algorithm. 

    2. Based on the learning data, DPA’s algorithm calculates the amount of wait time the database is likely to experience during each hour of the next 90 days and the standard deviation for the entire data set. (The standard deviation is used to calculate thresholds.) When enough data becomes available, DPA makes predictions about daily and weekly seasonality and patterns of predictable fluctuations during the day.

    DPA compares the actual wait time for an hour-long period and compares it to the predicted wait time, looking for discrepancies. If the actual wait time is above a critical threshold, DPA can do the following:

    • Trigger a Database Instance Wait Time Anomaly alert if one has been configured
    • Change the color of the wait time meter on the DPA homepage
    • Display yellow or red segments on the bars in the Anomaly Detection charts 
       

Why should I use anomaly detection in database monitoring?

Anomaly detection in a database, usually powered by machine learning, is a method of identifying unusual events in a database. Though databases can have outliers (and anomalies are outliers in most cases), not all outliers are anomalies. An anomaly detection tool can help DBAs more easily find “unusual” or “unexpected” instances based on database performance baselines, defining unusual and unexpected as “statistically improbable.”

Anomaly detection in database monitoring is ideal for the following:

  • Finding unusual metric values to identify undetected issues
  • Finding changes in important metrics for database administrators to investigate
  • Zeroing in on where to search when trying to diagnose a detected problem 
  • Reducing the need to recalibrate thresholds

DBAs can use anomaly detection in database monitoring to help drill down into what matters more quickly. A database anomaly detection tool can also alert DBAs to unusual changes potentially indicating a database performance problem before it grows into a bottleneck.

Close
How does machine learning help with anomaly detection?

Machine learning helps improve anomaly detection in a couple key areas:

  • Increases Accuracy: Machine learning makes anomaly-based monitoring for databases more accurate. To effectively highlight unusual events in your database, the anomaly detection tool must first establish a baseline of your database performance. However, these baselines change over time as you reoptimize and table tune. Machine learning can automatically account for these changes, recalibrate, and create new baselines, so DBAs have the most accurate data to work with. Also, machine learning can make the anomaly detection tool smarter over time, so its alerts become more accurate. 

  • Reduces Complexity: Machine learning uses automation and fast analysis to help database administrators break down large data sets so they can use them to create actionable tasks. It also helps reduce complexity in troubleshooting, as machine learning can point DBAs to where performance issues may be. This makes it so they don’t have to search the entire database for them. 

Close
How does anomaly-based database monitoring work in DPA?

Anomaly-based database monitoring in SolarWinds® Database Performance Analyzer (DPA) is built to help inform performance optimization efforts in two major ways:

  1. The machine learning algorithm learns what “normal” is for your database and predicts wait times. The algorithm requires a minimum of three days of data to start “learning” and can use up to 90 days of historical learning. DPA collects the data from the algorithm. 

  2. Based on the learning data, DPA’s algorithm calculates the amount of wait time the database is likely to experience during each hour of the next 90 days and the standard deviation for the entire data set. (The standard deviation is used to calculate thresholds.) When enough data becomes available, DPA makes predictions about daily and weekly seasonality and patterns of predictable fluctuations during the day.

DPA compares the actual wait time for an hour-long period and compares it to the predicted wait time, looking for discrepancies. If the actual wait time is above a critical threshold, DPA can do the following:

  • Trigger a Database Instance Wait Time Anomaly alert if one has been configured
  • Change the color of the wait time meter on the DPA homepage
  • Display yellow or red segments on the bars in the Anomaly Detection charts 
     

Close

Better optimize your databases with an anomaly detection tool

Database Performance Analyzer

  • Combine a robust anomaly detection tool with easy data drill downs, context setting, and consistent navigation.

  • Use a database anomaly detection tool to see what’s blocked and what’s doing the blocking.

  • Unlock the right data to get the most out of your database with SQL database anomaly detection.

Starts at {#Product Price#} Subscription and Perpetual Licensing options available
Let’s talk it over.
Contact our team. Anytime.
{#Contact Phone#}
multi-colored brand line
Close
{{STATIC CONTENT}}
{{CAPTION_TITLE}}

{{CAPTION_CONTENT}}

{{TITLE}}