Skip to content

Commit 50480c6

Browse files
PMEds28PMEds28
authored
Merge pull request #226019 from mrbullwinkle/mrb_02_01_2023_ad
[Cognitive Services] [Anomaly Detector] Service Limits
2 parents 8fa5edb + 3887e77 commit 50480c6

File tree

3 files changed

+101
-0
lines changed

3 files changed

+101
-0
lines changed

‎articles/cognitive-services/Anomaly-Detector/How-to/batch-inference.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -30,6 +30,8 @@ You could choose the batch inference API, or the streaming inference API for det
3030

3131
To perform batch inference, provide the blob URL containing the inference data, the start time, and end time. For inference data volume, at least `1 sliding window` length and at most **20000** timestamps.
3232

33+
To get better performance, we recommend you send out no more than 150,000 data points per batch inference. *(Data points = Number of variables * Number of timestamps)*
34+
3335
This inference is asynchronous, so the results aren't returned immediately. Notice that you need to save in a variable the link of the results in the **response header** which contains the `resultId`, so that you may know where to get the results afterwards.
3436

3537
Failures are usually caused by model issues or data issues. You can't perform inference if the model isn't ready or the data link is invalid. Make sure that the training data and inference data are consistent, meaning they should be **exactly** the same variables but with different timestamps. More variables, fewer variables, or inference with a different set of variables won't pass the data verification phase and errors will occur. Data verification is deferred so that you'll get error messages only when you query the results.

‎articles/cognitive-services/Anomaly-Detector/service-limits.md

Lines changed: 97 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,97 @@
1+
---
2+
title: Service limits - Anomaly Detector service
3+
titleSuffix: Azure Cognitive Services
4+
description: Service limits for Anomaly Detector service, including Univariate Anomaly Detection and Multivariate Anomaly Detection.
5+
services: cognitive-services
6+
author: jr-MS
7+
manager: nitinme
8+
ms.service: cognitive-services
9+
ms.subservice: anomaly-detector
10+
ms.topic: conceptual
11+
ms.date: 1/31/2023
12+
ms.author: jingruhan
13+
ms.custom:
14+
---
15+
16+
# Anomaly Detector service quotas and limits
17+
18+
This article contains both a quick reference and detailed description of Azure Anomaly Detector service quotas and limits for all pricing tiers. It also contains some best practices to help avoid request throttling.
19+
20+
The quotas and limits apply to all the versions within Azure Anomaly Detector service.
21+
22+
## Univariate Anomaly Detection
23+
24+
|Quota<sup>1</sup>|Free (F0)|Standard (S0)|
25+
|--|--|--|
26+
| **All APIs per second** | 10 | 500 |
27+
28+
<sup>1</sup> All the quota and limit are defined for one Anomaly Detector resource.
29+
30+
## Multivariate Anomaly Detection
31+
32+
### API call per minute
33+
34+
|Quota<sup>1</sup>|Free (F0)<sup>2</sup>|Standard (S0)|
35+
|--|--|--|
36+
| **Training API per minute** | 1 | 20 |
37+
| **Get model API per minute** | 1 | 20 |
38+
| **Batch(async) inference API per minute** | 10 | 60 |
39+
| **Get inference results API per minute** | 10 | 60 |
40+
| **Last(sync) inference API per minute** | 10 | 60 |
41+
| **List model API per minute** | 1 | 20 |
42+
| **Delete model API per minute** | 1 | 20 |
43+
44+
<sup>1</sup> All quotas and limits are defined for one Anomaly Detector resource.
45+
46+
<sup>2</sup> For **Free (F0)** pricing tier see also monthly allowances at the [pricing page](https://azure.microsoft.com/pricing/details/cognitive-services/anomaly-detector/)
47+
48+
### Concurrent models and inference tasks
49+
|Quota<sup>1</sup>|Free (F0)|Standard (S0)|
50+
|--|--|--|
51+
| **Maximum models** *(created, running, ready, failed)*| 20 | 1000 |
52+
| **Maximum running models** *(created, running)* | 1 | 20 |
53+
| **Maximum running inference** *(created, running)* | 10 | 60 |
54+
55+
<sup>1</sup> All quotas and limits are defined for one Anomaly Detector resource. If you want to increase the limit, please contact [email protected] for further communication.
56+
57+
## How to increase the limit for your resource?
58+
59+
For the Standard pricing tier, this limit can be increased. Increasing the **concurrent request limit** doesn't directly affect your costs. Anomaly Detector service uses "Pay only for what you use" model. The limit defines how high the Service may scale before it starts throttle your requests.
60+
61+
The **concurrent request limit parameter** isn't visible via Azure portal, Command-Line tools, or API requests. To verify the current value, create an Azure Support Request.
62+
63+
If you would like to increase your limit, you can enable auto scaling on your resource. Follow this document to enable auto scaling on your resource [enable auto scaling](../autoscale.md). You can also submit an increase Transactions Per Second (TPS) support request.
64+
65+
### Have the required information ready
66+
67+
* Anomaly Detector resource ID
68+
69+
* Region
70+
71+
#### Retrieve resource ID and region
72+
73+
* Go to [Azure portal](https://portal.azure.com/)
74+
* Select the Anomaly Detector Resource for which you would like to increase the transaction limit
75+
* Select Properties (Resource Management group)
76+
* Copy and save the values of the following fields:
77+
* Resource ID
78+
* Location (your endpoint Region)
79+
80+
### Create and submit support request
81+
82+
To request a limit increase for your resource submit a **Support Request**:
83+
84+
1. Go to [Azure portal](https://portal.azure.com/)
85+
2. Select the Anomaly Detector Resource for which you would like to increase the limit
86+
3. Select New support request (Support + troubleshooting group)
87+
4. A new window will appear with auto-populated information about your Azure Subscription and Azure Resource
88+
5. Enter Summary (like "Increase Anomaly Detector TPS limit")
89+
6. In Problem type, select *"Quota or usage validation"*
90+
7. Select Next: Solutions
91+
8. Proceed further with the request creation
92+
9. Under the Details tab enters the following in the Description field:
93+
* A note, that the request is about Anomaly Detector quota.
94+
* Provide a TPS expectation you would like to scale to meet.
95+
* Azure resource information you collected.
96+
* Complete entering the required information and select Create button in *Review + create* tab
97+
* Note the support request number in Azure portal notifications. You'll be contacted shortly for further processing.

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

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -9,6 +9,8 @@
99
href: https://aka.ms/adpricing
1010
- name: What's new
1111
href: whats-new.md
12+
- name: Service limits
13+
href: service-limits.md
1214
- name: FAQ
1315
href: faq.yml
1416
- name: Quickstarts

0 commit comments

Comments
 (0)