For more than 10 years, NMK Textile Mills has manufactured bed linens for major retailers in the United States and Canada. As e-commerce exploded, the company’s co-founder saw an opportunity to grow the business. So, in addition to manufacturing bed linens wholesale for retail customers, NMK Textile Mills reworked its complete supply chain to manufacture products for California Design Den, which became an e-commerce retailer selling its own fashion-forward products directly to consumers online.

With California Design Den’s push into e-commerce, it became apparent the SMB company (with about 250 global employees) faced the same tough supply chain questions as large retail customers, including maintaining enough inventory to meet customer demand in a timely, efficient way.

California Design Den depended upon a myriad of systems to track its complex forecasting and reordering processes. Team members typically planned inventory manually using desktop spreadsheet software, which could lead to excess inventory. Accurately forecasting demand and supply was essential to the company’s financial success—but it was also a challenge.

A couple years ago, California Design Den partnered with Pluto7, a technology solutions provider that offers a software as a service (SaaS) called Planning In A Box. Leveraging Google Cloud Platform machine learning and artificial intelligence, Planning In A Box intelligently helps predict demand and balances it with supply.

But that was just the beginning. “Along the way, we realized that to compete with larger retailers, make quicker decisions, and move faster, we needed to go further,” says Deepak Mehrotra, Co-founder and Chief Adventurer at California Design Den.

With guidance from Pluto7, California Design Den began migrating its database to Google Cloud Platform. Using Google BigQuery, Google Compute Engine, Google Cloud SQL, and Google Cloud Storage, and experimenting with Google Cloud Vision and Google Cloud AutoML, the company is reducing inventory carryovers by more than 50%, improving the accuracy of demand planning quarter over quarter, and gaining granular insights into how individual SKUs are performing.

“We would need an army of data scientists to make faster decisions on pricing and inventory levels. With Google Cloud Platform machine learning and artificial intelligence, we don’t need that. We can make much faster pricing decisions to optimize profitability and move inventory.”

—Deepak Mehrotra, Co-founder and Chief Adventurer, California Design Den

No need for army of data scientists

“Using Google Cloud Platform machine learning and AI was essential for California Design Den if it was to compete successfully with larger retailers,” Deepak says.

For example, tastes and fashions in bed linens can change quickly and consumer prices fluctuate. With more than 2,500 SKUs, it wasn’t possible for California Design Den’s team to continuously monitor product demand and experiment with competitive pricing in real time.

“We would need an army of data scientists to make faster decisions on pricing and inventory levels,” says Deepak. “With Google Cloud Platform machine learning and artificial intelligence, we don’t need that. We can make much faster pricing decisions to optimize profitability and move inventory.”

By integrating all its data onto Google Cloud Platform, California Design Den’s team gains deeper insights into product sales over time, which in turn helps the company improve demand planning by better determining which styles to manufacture and sell in the future.

“When experienced employees leave, their knowledge leaves with them. By having all data in one place, and with machine learning and AI, California Design Den can go back in its history, look at products made or sold years ago, and analyze product performance.”

—Deepak Mehrotra, Co-founder and Chief Adventurer, California Design Den

Merging visuals with data

Before Google Cloud Platform, team members had to dig through spreadsheets and run scenarios to get a sense of how particular products had sold. The next step was to perform keyword searches across the company’s photo library in the cloud to find each product’s image. From there, a team member would insert the product images into a presentation, along with relevant data points, to provide a report for stakeholders on how particular styles performed.

Today, California Design Den, with the help of Pluto7, is integrating its entire product image library with its database on Google Cloud Platform. Experimenting with Google Cloud Vision and Google Cloud AutoML, California Design Den is moving towards a day when team members can run sales scenarios and get deep background data on individual product performance while viewing images of the relevant products.

Merging product visuals with data will help designers and team members better understand sales patterns over time and in context. In the past, making correlations between things like which sheet colors sold well in California, compared to how the same sheet colors performed on the East Coast, was something that California Design Den employees primarily did in their heads.

“When experienced employees leave, their knowledge goes with them,” says Manjunath Devadas, Founder and CEO at Pluto7. “By having all data in one place, and with machine learning and AI, California Design Den can go back in its history, look at products made or sold years ago, and analyze product performance.”

“We are literally growing the complexity of our business on all levels, including designing, manufacturing, selling, reordering, inventory holding—everything.”

—Deepak Mehrotra, Co-founder and Chief Adventurer, California Design Den

Reimagining supply-demand balancing

Pluto7’s mission statement is to democratize supply demand balancing with machine learning and AI. California Design Den is a case in point, as the combination of Planning In A Box and Google Cloud Platform gives the company greater control over its destiny.

“Big retailers used to tell us what to manufacture and how much they would pay for it,” says Deepak. “That was our primary business, and if we didn’t accept the terms, a competitor would.” Today, in addition to continuing to make products for retailers, California Design Den can design, make, and sell a variety of designs for itself, including custom and limited-edition products, thanks to Google Cloud Platform and Pluto7 software offerings. The payoff is not only in having a more diversified business. California Design Den also receives more favorable profit margins by selling its own products.

“We are literally growing the complexity of our business on all levels, including designing, manufacturing, selling, reordering, inventory holding—everything,” Deepak says. “We can make smaller batches. We can connect directly with consumers. We can identify the missing pieces—what should we produce next, when, and how much? We otherwise couldn’t afford the level of talent it would take to do this.”

Cutting through the noise

Google and Pluto7 software helped California Design Den reduce inventory carryovers by more than 50%. Inventory tracking and distribution, along with insights and visibility into product sales, are faster, more efficient, and accurate. Google Cloud Platform flexible pricing, speed, reliability, security, and scalability enable California Design Den to stay relevant and be more competitive.

In addition to benefiting from Google Cloud Platform, California Design Den relies on G Suite—also part of Google Cloud—to enhance collaboration among its global teams. Previously, the company’s email server would sometimes crash, due to the heavy load of sharing product photos and other data. “Gmail and Google Drive handle the everyday demands on the business effortlessly and reliably,” Deepak says.

“Google machine learning and AI enable us to cut through all the noise from raw data, so we can see what’s important. We can focus on analytics to guide us to success today and in the future.”

—Deepak Mehrotra, Co-founder and Chief Adventurer, California Design Den

The company is exploring additional ways to leverage Google Cloud Platform in the near future. For example, one possibility is to import customer reviews from sites where products are sold into Google BigQuery, and to use that data to perform sentiment analysis via Google Cloud Natural Language. It could provide another valuable data source to help California Design Den’s team decide where to focus future designs.

“Google machine learning and AI enable us to cut through all the noise from raw data, so we can see what’s important,” Deepak says. “We can focus on analytics to guide us to success today and in the future.”

When you choose to run your business on Google Cloud you benefit from the same planet-scale infrastructure that powers Google’s products such as Maps, YouTube, and Workspace. 

We have picked 10 ways in which Google Cloud Infrastructure services outshine alternatives in the market in how they simplify your operations, save money, and secure your data. 

1. Custom Machine Types means no wasted resources

Compute Engine offers predefined machine types that you can use when you create a VM instance. A predefined machine type has a preset number of vCPUs and a preset amount of memory; each type is billed at a set price as described on the Compute Engine pricing page. 

If predefined machine types don’t meet your needs, you can create a VM instance with a custom number of vCPUs and custom amount of memory, effectively building a custom machine type. Custom machine types are available only for general-purpose machine families. When you create a custom machine type, you are deploying a custom machine type from the E2, N2, N2D, or N1 machine family on GCP.  No other leading cloud vendor offers custom machine types so extensively.

Custom machine types are a good idea for workloads that aren’t a good fit for the predefined machine types and for workloads that require more processing power or memory but don’t need all of the upgrades provided by the next machine type level. This translates into lower operating costs.   They are also useful for controlling software licensing costs that are based on the number of underlying compute cores. 

Jeremy Lloyd, Infrastructure and Application Modernization Lead at Appsbroker, a Google partner: 

“Custom machine types coupled with Google’s StratoZone data center discovery tool provides Appsbroker with the flexibility we need to provide cost efficient virtual machines matched to a virtual machine’s actual utilization. As a result, we are able to keep our customers’ operating costs low while still providing the ability to scale as needed.”

2. Compute Engine Virtual Machines are optimized for scale-out workloads 

For scale-out workloads, T2D, the first instance type in the Tau VM family, is based on 3rd Gen AMD EPYC processors and leapfrogs VMs for scale-out workloads of any leading public cloud provider today, both in terms of performance and price-performance. Tau VMs offer 56% higher absolute performance and 42% higher price-performance compared to general-purpose VMs from any leading public cloud vendor (source). The x86 compatibility provided by these AMD EPYC processor-based VMs gives you market-leading performance improvements and cost savings, without having to port your applications to a new processor architecture. Sign up here  if you are interested in trying out T2D instances in Preview. 

For SAP HANA, Google Cloud has demonstrated with SAP how we can run the world’s largest scale-out HANA system in the public cloud (96TB).   With such innovation, you are covered as your business grows exponentially.

3. Largest single node GPU-enabled VM

Google is the only public cloud provider to offer up to 16 NVIDIA A100 GPUs in a single VM, making it possible to train very large AI models. Users can start with one NVIDIA A100 GPU and scale to 16 GPUs without configuring multiple VMs for single-node ML training, without crossing the VM layer. 

Additionally, customers can choose smaller GPU configurations—1, 2, 4 and 8 GPUs per VM—providing the flexibility to scale their workload as needed. 

The A2 VM family was designed to meet today’s most demanding applications—workloads like CUDA-enabled machine learning (ML) training and inference, for example. This family is built on the A100 GPU which offers up to 20x the compute performance compared to the previous generation GPU and comes with 40 GB of high-performance HBM2 GPU memory. To speed up multi-GPU workloads, the A2 VMs use NVIDIA’s HGX A100 systems to offer high-speed NVLink GPU-to-GPU bandwidth that delivers up to 600 GB/s. A2 VMs come with up to 96 Intel Cascade Lake vCPUs, optional Local SSD for workloads requiring faster data feeds into the GPUs and up to 100 Gbps of networking. A2 VMs provide full vNUMA transparency into the architecture of underlying GPU server platforms, enabling advanced performance tuning. Google Cloud offers these GPUs globally. 

4. ​​Non-disruptive maintenance means you worry less about planned downtime

Compute Engine offers live migration (non-disruptive maintenance) to keep your virtual machine instances running even when a host system event, such as a software or hardware update, occurs. Google’s Compute Engine live migrates your running instances to another host in the same zone without requiring your VMs to be rebooted. Live migration enables Google to perform maintenance that is integral to keeping infrastructure protected and reliable without interrupting any of your VMs. When a VM is scheduled to be live-migrated, Google provides a notification to the guest that a migration is imminent. 

Live migration keeps your instances running during:

• Regular infrastructure maintenance and upgrades
• Network and power grid maintenance in the data centers
• Failed hardware such as memory, CPU, network interface cards, disks, power, and so on. This is done on a best-effort basis; if a hardware component fails completely or otherwise prevents live migration, the VM crashes and restarts automatically and a hostError is logged.
• Host OS and BIOS upgrades
• Security-related updates
• System configuration changes, including changing the size of the host root partition, for storage of the host image and packages

Live migration does not change any attributes or properties of the VM itself. The live migration process transfers a running VM from one host machine to another host machine within the same zone. All VM properties and attributes remain unchanged, including internal and external IP addresses, instance metadata, block storage data and volumes, OS and application state, network settings, network connections, and so on. This has the benefit of reducing operational and maintenance overhead, helps you build a more robust security posture where infrastructure can be consciously revamped from a known good state and minimizes risks for advanced persistent threats. 

Refer to Lessons learned from a year of using live migration in production on Google Cloud from the Google engineering team.

5. Trusted Computing: Shielded VMs guard you against advanced, persistent attacks

Establishing trust in your environment is multifaceted, involving hardware and firmware, as well as host and guest operating systems. Unfortunately, threats like boot malware or firmware rootkits can stay undetected for a long time, and an infected virtual machine can continue to boot in a compromised state even after you’ve installed legitimate software. 

Shielded VMs can help you protect your system from attack vectors like:

• Malicious guest OS firmware, including malicious UEFI extensions
• Boot and kernel vulnerabilities in the guest OS
• Malicious insiders within your organization

To guard against these kinds of advanced persistent attacks, Shielded VMs use:

• Unified Extensible Firmware Interface (UEFI) BIOS: Helps ensure that firmware is signed and verified
• Secure and Measured Boot: Helps ensure that a VM boots an expected, healthy kernel
• Virtual Trusted Platform Module (vTPM): Establishes root-of-trust, underpins Measured Boot, and prevents exfiltration of vTPM-sealed secrets
• Integrity Monitoring: Provides tamper-evident logging, integrated with Stackdriver, to help you quickly identify and remediate changes to a known integrity state

The Google approach allows customers to deploy Shielded VMs with only a simple click, thereby easing implementation. 

6. Confidential Computing encrypts data while in use

Google Cloud was a founding member of the Confidential Computing Consortium. Along with encryption of data in transit and at rest using customer-managed encryption keys (CMEK) and customer-supplied encryption keys (CSEK), Confidential VM adds a “third pillar” to the end-to-end encryption story by encrypting data while in use. Confidential Computing uses processor-based technology that allows data to be encrypted in use while it is being processed in the public cloud. Confidential VM allows you to to encrypt memory in use on a Google Compute Engine VM by checking a single checkbox. 

All Confidential VMs support the previously mentioned Shielded VM features under the covers—you can think of Shielded VM as helping to address VM integrity, while Confidential VM addresses the memory encryption aspect which relies on CPU features. With the confidential execution environments provided by Confidential VM and AMD Secure Encrypted Virtualization (SEV), Google Cloud keeps customers’ sensitive code and other data encrypted in memory during processing. Google does not have access to the encryption keys. In addition, Confidential VM can help alleviate concerns about risk related to either dependency on Google infrastructure or Google insiders’ access to customer data in the clear. 

See what Google Cloud partners say about Confidential Computing here. 

7. Advanced networking delivers full-stack networking and security services with fast, consistent, and scalable performance

Google Cloud’s network delivers low latency, reduces operational costs and ensures business continuity, enabling organizations to seamlessly scale up or down in any region to meet business needs. Our planet-scale network uses advanced software-defined networking and security with edge caching services to deliver fast, consistent, and scalable performance. With 28 regions, 85 zones, and 146 PoPs connected by 16 subsea fiber cables around the world, Google Cloud’s network offers a full stack of layer 1 to layer 7 services for enterprises to run their workloads anywhere. Enterprises can be assured that they have best-in-class networking and security services connecting their VMs, containers, and bare metal resources in hybrid and multi-cloud environments with simplicity, visibility, and control. 

Google Cloud’s network has protected customers from one of the world’s largest DDoS attacks at 2.54 Tbps. With our multi-layer security architecture and products such as Cloud Armor, our customers ran their business with no disruptions. Furthermore, our recent integration of Cloud Armor with reCAPTCHA Enterprise adds best-in-class bot and fraud management to prevent volumetric attacks. Cloud Armor is deployed with our Cloud Load Balancer and Cloud CDN, extending the secure benefits at the network edge for traffic coming into Google Cloud so customers have security, performance, and reliability all built in. Furthermore, we are excited to offer Cloud IDS in preview, which was co-developed with security industry leader, Palo Alto Networks, to run natively in Google Cloud. 

Our advanced networking capabilities also extends to GKE and Anthos networking. With the GKE Gateway controller, customers can manage internal and external HTTPS load balancing for a GKE cluster or a fleet of GKE clusters with multi-tenancy while maintaining centralized admin policy and control. Unlike other Kubernetes offerings, we offer eBPF dataplane which brings powerful tooling such as Kubernetes network policy and logging to GKE. eBPF is known to kernel engineers as a “superpower” for its unique architecture to load and unload modules in kernel space, and now this capability is built in with Google Cloud networking. 

For observability and monitoring, our customers deploy Network Intelligence Center, Google Cloud’s comprehensive network monitoring, verification and optimization platform. With four key modules in Network Intelligence Center, and several more to come, we are working towards realizing our vision of proactive network operations that can predict and heal network failures, driven by AI/ML recommendations and remediation. Network Intelligence Center provides unmatched visibility into your network in the cloud along with proactive network verification. Centralized monitoring cuts down troubleshooting time and effort, increases network security and improves the overall user experience.  

8. Regional Persistent Disk for High Availability

Regional Persistent Disk is a storage option that provides synchronous replication of data between two zones in a region. Regional Persistent Disks can be a great building block if you need to ensure high availability of your critical applications as they offer cost-effective durable storage and replication of data between two zones in the same region. 

Regional Persistent Disks are also easy to set up within the Google Cloud Console. If you are designing robust systems or high availability services on Compute Engine, Regional Persistent Disks combined with other best practices such as backing up your data using snapshots enable you to build an infrastructure that is highly available and recoverable in a disaster. Regional Persistent Disks are also designed to work with regional managed instance groups. In the unlikely event of a zonal outage, Regional Persistent Disks allow continued I/O through failover of your workloads to another zone. Regional Persistent Disks can help meet zero RPO and near-zero RTO requirements and other stringent SLAs that your critical applications might require by maximizing application availability and protection of data during events such as host/VM failures and zonal outages. 

9. Cloud Storage’s single namespace for dual-region and multi-region means managing regional replication is incredibly simple

Similar to how Persistent Disk makes data more available by replicating data across zones, Cloud Storage provides similar benefits for object storage. Cloud Storage within a region is cross-zone by definition, reducing the risk that a zonal outage would take down your application. Cloud Storage adds to this by also providing a cross-region option that can protect against a regional outage and gets your data closer to distributed users. This comes in the form of Dual-region or Multi-region settings for a bucket. These are the simplest to implement cross-region replication offerings in the industry—just a simple button or API call to enable them. In addition to being simple to implement, they offer an added advantage of using a single bucket name that spans regions. 

This is unique in the industry. Competitive offerings currently require setting up and managing two distinct buckets, one in each region and they don’t offer the strong consistency properties Cloud Storage offers across regions. Operations and app development are burdened by this design. Google’s single namespace approach dramatically simplifies application development (the app runs on single region or dual/multi-region without any changes), and provides simpler application restarts and testing for DR.

10. Predictive autoscaling 

Customers use predictive autoscaling to improve response times for applications with long initialization times or for applications with workloads that vary predictably with daily or weekly cycles. When you enable predictive autoscaling, Compute Engine forecasts future load based on your Managed Instance Group’s history and scales out the MIG’s in advance of predicted load, so that new instances are ready to serve when the load arrives. Without predictive autoscaling, an autoscaler can only scale a group reactively, based on observed changes in load in real time. 

With predictive autoscaling enabled, the autoscaler works with real-time data as well as with historical data to cover both the current and forecasted load. Forecasts are refreshed every few minutes (faster than competing clouds) and consider daily and weekly seasonality, leading to more accurate forecasts of load patterns.

For more information, see How predictive autoscaling works and Checking if predictive autoscaling is suitable for your workload.

These are just a few examples of customer-centric innovation that set Google Cloud infrastructure apart.  Bring your applications and let the platform work for you.   

Get started by learning about your options for migration, or talk to our sales team to join the thousands of customers who have embarked upon this journey.

Acknowledgement

Special thanks to Dheeraj Konidena (Google) for contributing to this article.

The COVID-19 pandemic tested our nation’s public benefits system in unimaginable ways. With an unprecedented 60 million individuals turning to unemployment and social services to satisfy their basic needs, state and local governments were stretched to meet the demand.

But state and local government leaders have risen to the challenge of providing their constituents with critical services. They created and administered innovative solutions, complete with wholly original processes, and brought desperately needed employment, cash, food, and healthcare support to families in crisis. These public sector heroes raised the bar during this critical time and facilitated economic recovery for our local communities, making the impossible possible for its people. 

When state and local government agencies partner with Google Cloud, they can reimagine how they deliver human services and labor services for their communities. All in a matter of weeks, instead of months or years.

Tools that solve for remote work and service delivery hurdles

Never before was there such a need for modern and accessible tools to allow a workforce to secure new jobs and operate remotely. The Virtual Career Center (VCC), built on Google Cloud, was designed with these needs in mind.

Google Workspace, including Google Meet, allows job seekers to schedule video meetings with career coaches, job recruiters, and potential employers. The Google Job Search API will enable them to explore career opportunities best suited to their skills and interests.

A thousand miles away, the Rhode Island Virtual Career Center was helping its job seekers by offering virtual meetings with career coaches, the ability to schedule meetings with prospective employers, and help on building effective resumes. Skipper, the CareerCompass RI Bot, an intelligent agent for careers, uses data and machine learning to facilitate potential new career paths and reskilling opportunities for Rhode Islanders.

In addition to enabling remote work, Google Workspace can support remote service delivery, a critical need for those involved in health and human services programs. Engaging with individuals and families is an essential component for more of these programs, including eligibility determination, assessment, and service delivery. The ability to engage directly with the public through virtual interviews, counseling sessions, telehealth, etc. improves access for those on both sides of the screen. Further, through Google Classroom, a component of Google Workspace for Education, foster and adoptive parents can obtain virtual training required for licensing. 

Tools to expedite relief funds and employment assistance

As the number of people applying for unemployment assistance skyrocketed, so did the backlog of claims requiring review. The pandemic also saw a rise in fraudulent claims, which caused delays for families waiting on legitimate payments and resulted in unnecessary spending for government agencies. Realizing the magnitude of the challenge was beyond the agencies’ current resources, and they shifted their focus to machine learning.  

To address the massive backlog of claims, SpringML partnered with Google Cloud to develop the Improper Payment Analytics solution that successfully leverages AI to help agencies identify fraudulent claims and avoid improper payments so aid can be prioritized for those who need it. Though such a tool would typically take months to develop, the team was able to launch it in just weeks, to the benefit of all stakeholders involved. Families awaiting legitimate payments received checks more quickly, and state and local governments saved millions in spending.

For instance, to address erroneous payments totaling $330 million to fraudulent applicants, the State of Ohio partnered with Google Cloud to utilize artificial intelligence and machine learning solutions to proactively identify and decline improper payment risks. As a result, the State avoided paying fraudulent claims and accelerated the payment of legitimate benefits to families facing financial hardship.

The New York State Department of Labor launched a streamlined unemployment application to allow residents to apply for pandemic unemployment assistance without the added burden of applying for unemployment insurance. Success was immediate, and the application backlog plummeted as New Yorkers got the financial aid they desperately needed. Illinois took a different approach, deploying Contact Center Artificial Intelligence (CCAI) to create virtual agents who assist with specialized calls 24/7, in multiple languages, providing turn-by-turn guidance in real-time. Conversations can be turned into insights through analytics and reporting tools that uncover key call drivers and customer sentiment. By solving for spikes in call volume, CCAI has helped process more than 1 million unemployment claims.

Automated data solutions bring immediate food and cash assistance resources

With millions out of work and out of school during the pandemic, food and cash assistance became a critical need. Applying for all of these benefits requires significant documentation that, in most cases, has historically been manually processed. Given the volume of people in need, this took a massive amount of human resources and time.

Using Document AI (DocAI), agencies can automate this highly manual process and speed up the delivery of critical benefits to individuals and families. DocAI extracts the key data, provides a confidence score in a single review pane for staff review, and automatically uploads that data to the case management system–significantly reducing manual processing. Today, these state and local government organizations turn to DocAI to eliminate the difficult paperwork application process to help meet the benefit needs of their residents now and tomorrow, as illustrated by both the Wisconsin Department of Workforce Development (DWD) and the State of Hawaii.

The Wisconsin DWD streamlined their paper unemployment insurance claims using DocAI by enabling DWD staff to receive critical data extracted from submitted applications and make decisions rapidly, saving time for both applicants and staff. The State of Hawaii also used DocAI to extract, interpret, and transport COVID-19 test result data of incoming travelers to Google Cloud instantly. As a result, Hawaii was able to welcome travelers and reopen its economy in the midst of the pandemic.

Partner with us

After making it through this very difficult period, agencies have emerged from the pandemic with stronger labor and health and human service delivery for their residents. State and local governments recognized the necessity of virtual engagement and expanded access to services to meet this critical moment, solving for work, cash, food and healthcare needs.

To learn more about Google Cloud for human services and labor, watch our video on the power of customer innovation or contact your Google Cloud sales representative. Let’s get solving together.

The past year has given everyone lots to think about—about our priorities as people and as businesses. As the world retreated behind closed doors, we saw how shared interests and experiences can bring us together. As the world grappled with a common enemy, we witnessed just how differently individuals, communities and indeed entire countries can experience a situation. And as we faced seemingly unending obstacles to making it through the pandemic, we saw how making smart decisions based on data can drive meaningful solutions—fast.

That’s why we here at Google Cloud are so proud to partner Univision, the country’s leading Spanish-language content and media company. By partnering with Google Cloud, Univision will be able to accelerate growth across its portfolio of properties, deliver an enhanced user experience for Spanish-speaking audiences and provide the enterprise solutions needed to create the Spanish-language media company of the future.

According to Instituto Cervantes, there are over 580 million Spanish language speakers worldwide. Those viewers, like people everywhere, are avid consumers of streaming content. In Q4 of 2020 alone, viewing time for that content increased by 44%¹, and in 2020, from 50%² more sources. With that surge in demand, Univision needed a cloud provider whose infrastructure could reach Hispanic viewers around the world. With two-plus decades spent building out its network and data centers, as well as global content-delivery capabilities, Google Cloud has the infrastructure Univision needs to reach viewers across the Spanish-speaking world.

At the same time, with such a diverse audience for their content, Univision needs to target that content to viewers’ specific preferences. By applying Google Cloud’s artificial intelligence (AI) and machine learning (ML) technology across its content, Univision intends to personalize content based on shows users have previously watched, enhancing their engagement and viewing experience. 

And as Univision transforms the user experience, it can use Google Cloud’s data and analytics suite to garner deeper insights into its audience and forge stronger relationships with them on an individual basis. With Looker and BigQuery, Univision employees will have access to real-time data to help them make business decisions about programming.

Univision will also migrate video distribution and production operations to Google Cloud, where we’ll help them streamline media workflows and develop innovative new capabilities. Meanwhile, Google Cloud’s tight business and technical integration with other Google services will help ensure Univision reaches viewers on the device of their choice, wherever they are in the world. For example, in the coming years, Univision will expand its global YouTube partnership and will integrate with entertainment features on Google Search that help people better discover TV shows and movies. The company will also use Google Ad Manager for global ad decisioning and Google’s Dynamic Ad Insertion for PrendeTV and future video-on-demand offerings. Finally, Univision will distribute its content and services on Google Play across Android phones and tablets, as well as Google TV and other Android TV OS devices.

We’re thrilled to partner with Univision to help them reach the Spanish-speaking world with their content. With our cloud portfolio, we can help them reach individual viewers around the world, with personalized content that they can consume however they see fit. Best of all, together, we can help them achieve this vision fast, leveraging established cloud, content delivery, and data analytics technologies. You can learn more about the partnership here.

When you build a Machine Learning (ML) product, consider at least two MLOps scenarios. First, the model is replaceable, as breakthrough algorithms are introduced in academia or industry. Second, the model itself has to evolve with the data in the changing world.

We can handle both scenarios with the services provided by Vertex AI. For example:

• AutoML capability automatically identifies the best model based on your budget, data, and settings.
• You can easily manage the dataset with Vertex Managed Datasets by creating a new dataset or adding data to an existing dataset.
• You can build an ML pipeline to automate a series of steps that start with importing a dataset and end with deploying a model using Vertex Pipelines.

This blog post shows you how to build this system. You can find the full notebook for reproduction here. Many folks focus on the ML pipeline when it comes to MLOps, but there are more parts to building MLOps as a “system”. In this post, you will see how Google Cloud Storage (GCS) and Google Cloud Functions manage data and handle events in the MLOps system.

Architecture

Figure 1 shows the overall architecture presented in this blog. We cover the components and their connection in the context of two common workflows of the MLOps system.

Components

Vertex AI is at the heart of this system, and it leverages Vertex Managed Datasets, AutoML, Predictions, and Pipelines. We can create and manage a dataset as it grows using Vertex Managed Datasets. Vertex AutoML selects the best model without your knowing much about modeling. Vertex Predictions creates an endpoint (RestAPI) to which the client communicates.

It is a simple, fully managed yet somewhat complete end-to-end MLOps workflow moves from a dataset to training a model that gets deployed. This workflow can be programmatically written in Vertex Pipelines. Vertex Pipelines outputs the specification for an ML pipeline allowing you to re-run the pipeline whenever or wherever you want. Specify when and how to trigger the pipeline using Cloud Functions and Cloud Storage.

Cloud Functions is a serverless way to deploy your code in Google Cloud. In this particular project, it triggers the pipeline by listening to changes on the specified Cloud Storage location. Specifically, if a new dataset is added, for example, a new span number is created; the pipeline is triggered to train the dataset, and a new model is deployed.

Workflow

This MLOps system prepares the dataset with either Vertex Dataset’s built-in user interface (UI) or any external tools based on your preference. You can upload the prepared dataset into the designated GCS bucket with a new folder named SPAN-NUMBER. Cloud Functions then detects the changes in the GCS bucket and triggers the Vertex Pipeline to run the jobs from AutoML training to endpoint deployment.

Inside the Vertex Pipeline, it checks if there is an existing dataset created previously. If the dataset is new, Vertex Pipeline creates a new Vertex Dataset by importing the dataset from the GCS location and emits the corresponding Artifact. Otherwise, it adds the additional dataset to the existing Vertex Dataset and emits an artifact.

When the Vertex Pipeline recognizes the dataset as a new one, it trains a new AutoML model and deploys it by creating a new endpoint. If the dataset isn’t new, it tries to retrieve the model ID from Vertex Model and determines whether a new AutoML model or an updated AutoML model is needed. The second branch determines whether the AutoML model has been created. If it hasn’t been created, the second branch creates a new model. Also, when the model is trained, the corresponding component emits the artifact as well.

Directory structure that reflects different distributions

In this project, I have created two subsets of the CIFAR-10 dataset, SPAN-1 and SPAN-2. A more general version of this project can be found here, which shows how to build training and batch evaluation pipelines pipelines. The pipelines can be set up to cooperate so they can evaluate the currently deployed model and trigger the retraining process.

ML Pipeline with Kubeflow Pipelines (KFP)

We chose to use Kubeflow Pipelines to orchestrate the pipeline. There are a few things that I would like to highlight. First, it’s good to know how to make branches with conditional statements in KFP. Second, you need to explore AutoML API specifications to fully leverage AutoML capabilities, such as training a model based on the previously trained one. Last, you also need to find a way to emit artifacts for Vertex Dataset and Vertex Model to consume that Vertex AI can recognize them. Let’s go through these one by one.

Branching strategy

In this project, there are two main conditions and two sub-branches inside the second main branch. The main branches split the pipeline based on a condition if there is an existing Vertex Dataset. The sub-branches are applied in the second main branch, which is selected when there is an exciting Vertex Dataset. It looks up the list of models and decides to train an AutoML model from scratch or a previously trained one.

ML pipelines written in KFP can have conditions with a special syntax of kfp.dsl.Condition. For instance, we can define the branches as follows:

from google_cloud_pipeline_components import aiplatform as gcc_aip


# try to get Vertex Dataset ID
dataset_op = get_dataset_id(...) 

with kfp.dsl.Condition(name="create dataset", 
                       dataset_op.outputs['Output'] == 'None'):
    # Create Vertex Dataset, train AutoML from scratch, deploy model

with kfp.dsl.Condition(name="update dataset", 
                       dataset_op.outputs['Output'] != 'None'):
    # Update existing Vertex Dataset
    ...

    # try to get Vertex Model ID
    model_op = get_model_id(...)

    with kfp.dsl.Condition(name='model not exist',
                           model_op.outputs['Output'] == 'None'):
    # Create Vertex Dataset, train AutoML from scratch, deploy model

    with kfp.dsl.Condition(name='model exist',
                           model_op.outputs['Output'] != 'None'):
        # Create Vertex Dataset, train AutoML based on trained one, deploy model

get_dataset_id and get_model_id are custom KFP components used to determine if there is an existing Vertex Dataset and Vertex Model respectively. Both return “None” if a model is found and some other value if a model isn’t found. They also emit Vertex AI-aware artifacts. You will see what this means in the next section.

Emit Vertex AI-aware artifacts

Artifacts track the path of each experiment in the ML pipeline and display metadata in the Vertex Pipeline UI. When Vertex AI aware artifacts are released into in the pipeline, Vertex Pipeline UI displays links for its internal services such as Vertex Dataset, so that users can visit a web page for more information.

So how could you write a custom component to generate Vertex AI-aware artifacts? To do this, custom components should have Output[Artifact] in their parameters. Then you need to replace the resourceName of the metadata attribute with a special string format.

The following code example is the actual definition of get_dataset_id used in the previous code snippet:

@component(
    packages_to_install=["google-cloud-aiplatform", 
                         "google-cloud-pipeline-components"]
)
def get_dataset_id(project_id: str, 
                     location: str,
                 dataset_name: str,
                 dataset_path: str,
                      dataset: Output[Artifact]) -> str:
    from google.cloud import aiplatform
    from google.cloud.aiplatform.datasets.image_dataset import ImageDataset
    from google_cloud_pipeline_components.types.artifact_types import VertexDataset

    
    aiplatform.init(project=project_id, location=location)
    
    datasets = aiplatform.ImageDataset.list(project=project_id,
                                            location=location,
                                            filter=f'display_name={dataset_name}')
    
    if len(datasets) > 0:
        dataset.metadata['resourceName'] = 
               f'projects/{project_id}/locations/{location}/datasets/{datasets[0].name}'
        return f'projects/{project_id}/locations/{location}/datasets/{datasets[0].name}'
    else:
        return 'None'

As you see, the dataset is defined in the parameters as Output[Artifact]. Even though it appears in the parameter, it is actually emitted automatically. You just need to provide the necessary data as if it is a function variable.

The dataset component retrieves the list of Vertex Dataset by calling the aiplotform.ImageDataset.list API. If the length of it is zero, it simply returns ‘None’. Otherwise, it returns the found resource name of the Vertex Dataset and provides the dataset.metadata[‘resourceName’] with the resource name at the same time. The Vertex AI-aware resource name follows a special string format, which is ‘projects/<project-id>/locations/<location>/<vertex-resource-type>/<resource-name>’.

The <vertex-resource-type>can be anything that points to an internal Vertex AI service. For instance, if you want to specify that the artifact is the Vertex Model, then you should replace <vertex-resource-type> with models. The <resource-name> is the unique ID of the resource, and it can be accessed in the name attribute of the resource found by the aiplatform API. The other custom component, get_model_id, is written in a very similar way as well.

AutoML based on the previous model

You sometimes want to train a new model on top of the previously best model. If that is possible, the new model will probably be much better than the one trained from scratch, because it leverages previously learned knowledge.

Luckily, Vertex AutoML comes with the ability to train a model using a previous model. AutoMLImageTrainingJobRunOp component lets you train a model by simply providing the base_model argument as follows:

training_job_run_op =
gcc_aip.AutoMLImageTrainingJobRunOp(
…,
base_model=model_op.outputs['model'],
…
)

When training a new AutoML model from scratch, you pass ‘None‘ in the base_model argument, and it is the default value. However, you can set it with a VertexModel artifact, and the component will trigger an AutoML training job based on the other model.

One thing to be careful of is that VertexModel artifacts can’t be constructed in a typical way of Python programming That means you can’t create an instance of VertexModel artifact by setting the id found in the Vertex Model dashboard. The only way you can create one is to set the metadata[‘resourceName’] parameters properly. The same rule applies to other Vertex AI-related artifacts such as VertexDataset. You can see how the VertexDataset artifact is constructed properly to get an existing Vertex Dataset to import additional data into it. See the full notebook of this project here.

Cost

You can reproduce the same result from this project with the free $300 credit when you create a new GCP account.

At the time of this blog post, Vertex Pipelines costs about $0.03/run, and the type of underlying VM for each pipeline component is e2-standard-4, which costs about $0.134/hour. Vertex AutoML training costs about $3.465/hour for image classification. GCS holds the actual data, which costs about $2.40/month for 100GiB capacity, and Vertex Dataset is free.

To simulate two different branches, the entire experiment took about one to two hours, and the total cost for this project is approximately $16.59. Please find more detailed pricing information about Vertex AI here.

Conclusion

Many people underestimate the capability of AutoML, but it is a great alternative for app and service developers who have little ML background. Vertex AI is a great platform that provides AutoML as well as Pipeline features to automate the ML workflow. In this article, I have demonstrated how to set up and run a basic MLOps workflow, from data injection to training a model based on the previously-achieved best one, to deploying the model to a Vertex AI platform. With this, we can let our ML model automatically adapt to the changes in a new dataset. What’s left for you to implement is to integrate a model monitoring system to detect data/model drift. One example is found here.