Merge pull request #216156 from mrbullwinkle/mrb_10_27_2022_ad_faq

[Cognitive Services] [Anomaly Detector] FAQ doc

Author: v-dirichards

articles/cognitive-services/Anomaly-Detector/faq.yml

@@ -0,0 +1,52 @@
+### YamlMime:FAQ
+metadata:
+  title: Frequently asked questions - Anomaly Detector
+  titleSuffix: Azure Cognitive Services
+  description: Get answers to frequently asked questions about the Anomaly Detector Service in Azure Cognitive Services.
+  ms.service: cognitive-services
+  ms.subservice: anomaly-detector
+  ms.topic: faq
+  ms.date: 11/1/2022
+  ms.author: jingruhan
+  author: jr-MS
+  ms.manager: nitinme
+title: Anomaly Detector frequently asked questions
+summary: This article contains answers to frequently asked troubleshooting questions about the Anomaly Detector service.
+
+
+sections:
+
+  - name: Anomaly Detector frequently asked questions
+    questions: 
+      - question: |
+          When to use Univariate Anomaly Detection v.s. Multivariate Anomaly Detection?
+        answer:  |
+          If your goal is to detect anomalies out of a normal pattern on each individual time series purely based on their own historical data, use the univariate anomaly detection APIs. For example, you want to detect daily revenue anomalies based on revenue data itself, or you want to detect a CPU spike purely based on CPU data.
+          If your goal is to detect system level anomalies from a group of time series data, use multivariate anomaly detection APIs. Particularly, when any individual time series won't tell you much, and you have to look at all signals (a group of time series) holistically to determine a system level issue. For example, you have an expensive physical asset like aircraft, equipment on an oil rig, or a satellite. Each of these assets has tens or hundreds of different types of sensors. You would have to look at all those time series signals from those sensors to decide whether there's system level issue.
+      - question: |
+          Can the Anomaly Detector service be used in other platforms or applications?
+        answer:  |
+          Anomaly Detector is now integrated into Power BI, Azure Data Explorer, and Azure Synapse. You could also use our service in Azure Machine Learning, and Azure Databricks. 
+      - question: |
+          Is Anomaly Detector available in my Azure region?
+        answer:  |
+          Anomaly Detector is generally available in many of the [30+ Azure global infrastructure regions](https://azure.microsoft.com/en-us/explore/global-infrastructure/products-by-region/?products=cognitive-services&regions=all).
+          Choose the region that is best for you and your customers.
+      - question: |
+          Can Anomaly Detector be deployed to the edge?
+        answer:  | 
+          [Use Univariate Anomaly Detector containers](anomaly-detector-container-howto.md) to deploy API features on-premises. Docker containers enable you to bring the service closer to your data for compliance, security, or other operational reasons. Multivariate Anomaly Detection doesn't currently support containers.
+      - question: |
+          Is the Anomaly Detector service zone resilient?
+        answer:  |
+          Yes. The Anomaly Detector service is zone-resilient by default.
+      - question: |
+          How do I configure the Anomaly Detector service to be zone-resilient?
+        answer:  |
+          No customer configuration is necessary to enable zone-resiliency. Zone-resiliency for Anomaly Detector resources is available by default and managed by the service itself.
+
+additionalContent: |
+  ## Next steps
+     * [What is the Anomaly Detector API?](overview.md)
+     * [Anomaly detection methods](how-to/identify-anomalies.md)
+     * [Best practices when using the Anomaly Detector API.](concepts/anomaly-detection-best-practices.md) 

articles/cognitive-services/Anomaly-Detector/toc.yml

@@ -13,6 +13,8 @@
       href: https://aka.ms/adpricing
     - name: What's new
       href: whats-new.md
+    - name: FAQ
+      href: faq.yml
 - name: Quickstarts
   items:
     - name: Client libraries (univariate)