In recent years, machine learning (ML) has gained tremendous popularity as a powerful tool for solving complex problems across various domains. However, building and deploying ML models at scale can be challenging, as it involves a range of tasks such as data preparation, feature engineering, model training, deployment, monitoring, maintenance and so on. 

According to “The Art of AI maturity” report published by Accenture “87% of data science projects never make it into production.” This is where MLOps comes in – it can help to address the core challenges by providing a framework for managing the entire ML lifecycle, from data collection and preparation to model development, testing, and deployment. It also reduces the time from ML model development to production and increases the success rate of ML projects.

In Google Cloud, we understand how important MLOps is to successfully productionize ML models. So we collaborated with Equinix, the world’s digital infrastructure company™ and  a leader in global colocation data center market share, with 248 data centers in 27 countries on five continents. We helped them by providing the advisory services on the MLOps best practices and architecture. 

Let’s take a sneak peek at the MLOps requirements at Equinix and the final architecture that was proposed.

What does MLOps mean for Equinix?

After multiple discovery sessions with the Equinix Team, we identified the core requirements and pain points to address in their new MLOps architecture:

• Reusability: Components such as features and pipeline components should be reused across projects to reduce costs and improve efficiency.
• Foundations: The foundations of the infrastructure, such as environments, folder structure, and project hierarchy, should be well-designed to support scalability and reliability.
• Early identification of problems: Problems should be identified early by including data validation, notifications, and retry mechanisms.
• Cost optimization: Costs should be optimized by paying only for what is used.
• Enterprise CI/CD requirements: Enterprise CI/CD requirements should be met by integrating with GitHub and GitActions.
• Scaling: The infrastructure must scale to support future growth.
• Security: Enterprise security requirements should be met in terms of IAM roles, network, etc.

MLOps Architecture

Based on the above requirements from Equinix, key design considerations were made for example – using Vertex AI Feature Store instead of Big Query for online feature serving, using DataFlow for pre-processing vs using the existing python based pre-processing and so on. After carefully assessing all the alternatives, the below reference architecture for MLOps in GCP was proposed:

Reference architecture for MLOPs using GCP is illustrated in Figure 1. This architecture includes the following pipeline stages:

• Vertex AI Workbench enables data scientists to quickly explore new ideas and develop/experiment new models. The source code is saved in GitHub repository
• Github Actions with self-hosted runners are integrated with Github as the source code repository. This enables continuous integration of code, quality and security scans. The artifacts generated during the process are saved in Artifact Registry and Google Cloud Storage. These artifacts are deployed to implement the pipeline.
• Unit tests and integration tests can be performed during the continuous integration in Github Actions with self-hosted runners. End-to-end tests are performed on demand in the continuous integration pipeline. 
• Metadata about the artifacts is generated and saved in Vertex ML Metadata.
• Automated triggers can be enabled to run pipelines. For example, one trigger is the availability of new training data. These triggers can run the model training pipeline and the new trained model can be pushed to Vertex AI Model Registry.
  • To train a new ML model with new data, the deployed Vertex AI Pipeline is executed. 
  • To train a new ML model with new implementation, a new pipeline will be deployed through CI/CD pipeline.

“The proposed architecture design covers the requirements and scenarios that we were looking for. As our AI and ML portfolio is growing in scale and complexity, it’s important to follow a clear and up-to-date architecture if we want to keep increasing the value delivered by our solutions. As part of the process, the team also acquired the skills required to fully implement it” according to Bernardo Fernandes, Data Science Senior Manager at Equinix.

Below is the snapshot of the features before and after MLOps implementation at Equinix:

As businesses increasingly rely on machine learning to gain a competitive edge, MLOps has become a critical component of their strategy. By adopting MLOps practices, organizations can achieve faster time-to-market, better performance, and higher ROI for their machine learning initiatives.

Fast track end-to-end deployment with Google Cloud AI Services (AIS)

The partnership between Google Cloud and Equinix is just one of the latest examples of how we’re providing AI-powered solutions to solve complex problems to help organizations drive the desired outcomes. To learn more about Google Cloud’s AI services, visit our AI & ML Products page.

^{We’d like to give special thanks to Nitin Aggarwal, Vijay Surampudi, Parag Mhatre and Anantha Narayanan Krishnamurthy for their support and guidance throughout the project. We are also grateful to the super awesome collaboration with the Equinix Team (Ravi Pasula and Brendan Coffey, Bernardo Fernandes, Łukasz Murawski, Jakub Michałowski, Sonia Przygocka-Groszyk, Marek Opechowski, Daria Bondara, Nila Velu, Vijay Narayanan, Dharmendra Kumar, Shailesh Sukare, Arunraj Kumar Raje, Seng Cheong Lee).}

The magnitude and direction of wind significantly impacts airport operations, and Lufthansa Group Airlines are no exception. A particularly troublesome kind is called BISE: it is a cold, dry wind that blows from the northeast to southwest in Switzerland, through the Swiss Plateau. Its effects on flight schedules can be severe, such as forcing planes to change runways, which can create a chain reaction of flight delays and possible cancellations. In Zurich Airport, in particular, BISE can potentially reduce capacity by up to 30%, leading to further flight delays and cancellations, and to millions in lost revenue for Lufthansa (as well as dissatisfaction among their passengers).

Being able to predict this kind of wind well in advance lets the Network Operations Control team schedule flight operations optimally across runways and timeslots, to minimize disruptions to the schedule. However, predicting speed and magnitude can be incredibly difficult to model and thus to predict— which is why Lufthansa reached out to Google Cloud.

Machine learning (ML) can help airports and airlines to better anticipate and manage these types of disruptive weather events. In this blog post, we’ll explore an experiment Lufthansa did together with Google Cloud and its Vertex AI Forecast service, accurately predicting BISE hours in advance, with more than 40% relative improvement in accuracy over internal heuristics, all within days instead of the months it often takes to do ML projects of this magnitude and performance.

“Being impressed with Google’s technology and prowess in the field of AI and machine learning, we were certain that my working together with their expert, to combine our technology with their domain expertise, we would achieve the best results possible,“ said Christian Most, Senior Director, Digital Operations Optimization at Lufthansa Group.

Collecting and preparing the dataset

The goal of Lufthansa and Google Cloud’s project was to forecast the BISE wind for Zurich’s Kloten Airport using deep learning-based ML approaches, then to see if the prediction surpasses internal heuristics-driven solutions and gauge the ease of use and practicality of the deep learning approach in production.

Since deep learning-based techniques require large datasets, the project relies on Meteoswiss simulation data, a dataset consisting of multiple meteorological sensor measurements collected from several weather stations across Switzerland over the past five years. By using this dataset, we obtained data on factors like wind direction, speed, pressure, temperature, humidity and more, at a 10 min resolution, along with some information about the location of the weather stations, such as altitude. These factors, which we hypothesized to be predictive of the BISE, ended up carrying valuable signals, as we would see later.

This collected data was next subjected to an extensive cleaning and feature engineering process using Vertex AI Workbench, in order to prepare the final dataset for training. The cleaning phase included steps to drop the features, or rows, that contained too many missing values, or failed statistical tests for entropy, etc. Since the direction of wind is a circular feature (between 0 and 360 degrees), this column/feature was replaced with two features: the corresponding sine and cosine embedding. The dataset was then flattened such that the columns contained all the relevant features and sensor measurements from all the weather stations at a particular 10-minute interval.

Since the target variable — i.e,. BISE — was not directly available, we engineered a proxy target variable for BISE called “tailwind speed around runway,” which above a certain threshold indicates the presence of BISE along the runway.

Forecasting wind in the Cloud

Once the dataset was ready, Lufthansa and Google Cloud evaluated several options before deciding to experiment and tune Vertex AI Forecast, Google’s AutoML-powered forecasting service, in order to achieve optimum results. Vertex Forecast is capable of the required feature engineering, neural architecture search, and hyper parameter tuning, and it is managed by Google Cloud to score in the top 2.5% in the M5 Forecasting Competition on Kaggle, in a completely automated fashion. These qualities made it an excellent choice for Lufthansa, to reduce the manual overhead of creating, deploying, and maintaining top performing deep learning models.

The raw data files were loaded from cloud storage, preprocessed on Vertex AI Workbench. Then, a training pipeline was initiated on Vertex AI Pipelines, which performed the following steps in sequence:

The .csv data file was loaded from Cloud Storage into a Vertex AI managed dataset.

A Vertex AI forecasting training job was initiated with the dataset, and it was also registered as a model in the Vertex AI Model Registry.

Upon completion, the model was evaluated on the test set, and the model’s predictions and the input features and ground truth of the test set, were stored in a user-defined table in BigQuery. Several test metrics were also available on the service and model dashboards.

One of the biggest challenges was the severe imbalance in the dataset, as measurements with BISE were very far and few in between. In order to account for this, instances where BISE occurred, as well the occurrences temporally close to them, were upweighted using weights calculated with methods including Inverse of Square Root of Number of Samples (ISNS), Effective Number of Samples (ENS), and Gaussian reweighting. The formulas for the methods are given below. These weights were supplied as separate columns in the dataset, and were iteratively used thereafter by the service as the “weight” column.

ISNS

ENS

Weighted gaussian

Results and next steps

In the above figures, the x-axis represents the forecast horizon and the Y-axis shows the respective metrics (Recall/F1-score). As shown after multiple experiments, we can see Vertex AI Forecast achieved higher recall and precision t (red bar), outperforming Lufthansa’s internal baseline heuristics, with the performance gap widening steadily as the forecast horizon extends further into the future. At the two-hour mark, our custom-configured Vertex AI Forecast model improved by 40% relative to the internal heuristics and 1700% compared to the random guess baseline. As we saw with other experiments, at a six-hour forecast horizon, the performance gap widens even more, with Vertex AI Forecast in the lead. Since forecasting BISE a few hours in advance is very beneficial to prevent flight delays for Lufthansa, this was a great solution for them.

“We are very excited to be able to not only do accurate long term forecasts for the BISE, but also that Vertex AI Forecasting makes training and deploying such models much easier and faster, allowing us to innovate rapidly to serve our customers and stakeholders in the best possible manner,” said Swiss Oliver Rueegg, Product Owner, Swiss International Airlines.

Lufthansa plans to explore productionizing this solution by integrating it into their Operations Decision Support Suite, which is used by the network controllers in the Operations Control Center in Kloten, as well as to work closely with Google’s specialists to integrate both Vertex AI Forecast and other of Google’s AI/ML offerings for their use cases.

“Talk about tough times, right?”

That’s how Dan Stuart, Senior Vice President of IT Services at Southwire Company, refers to the months following a December 2019 ransomware event, and the COVID crisis that began in spring of 2020. Those events hit just as the company was preparing for an overhaul of their SAP environment. This comprehensive plan included three key elements. First, the company wanted to upgrade their SAP ECC environment to take advantage of the latest functionality available for this critical ERP system. Second, Southwire aimed to deploy SAP Business Warehouse on SAP HANA to accelerate vital reporting for all business users. Third, the company wanted to upgrade to the latest version of SAP Process Orchestration—an essential component that touches key manufacturing interfaces in all Southwire facilities. 

Southwire had looked at multiple options for the upgrades, including remaining entirely on-premises, colocation, and full cloud migration. “Going to the cloud seemed a lot more compelling,” says Joe Schleupner, Southwire’s Senior Director of PMO & ITS planning and implementation. “We were going to the cloud eventually, so why take these intermediary steps? Let’s just get it done.”

After looking at several options, Southwire decided to migrate to Google Cloud. “We wanted to be on a platform for SAP that was flexible, scalable, and secure; that we could count on to get up and running quickly,” says Stuart. “We chose Google Cloud not only for those reasons, but also because we recognize that Google has other assets that we may be able to take advantage of down the line, such as technologies like artificial intelligence (AI).” 

More stability, less worry

As one of the leading manufacturers of wire and cable used in the transmission and distribution of electricity, Southwire aids the delivery of power to millions of people worldwide. They have more than 30 manufacturing facilities across the United States running 24/7. Any downtime directly affects productivity and revenue. With help from Google Cloud and their implementation partner NIMBL, Southwire completed the SAP migration to Google Cloud over a planned maintenance weekend on July 4th.

The migration itself, while complex, went quickly and smoothly. “Just moving to the cloud was quite a feat because we were dealing with so much data, but in total the SAP system was down for only ~16 hours,” says Schleupner.

“As a project manager, I always felt that Google Cloud had my back” Schleupner says. The Process Orchestration (PO) migration was of particular concern, considering that it controlled all of Southwire’s manufacturing interfaces across the entire company. “Every critical piece of information that goes from SAP down to the manufacturing system goes through that system,” says Schleupner.

Even after migrating, Southwire discovered that making changes to the system was fast, easy, and resulted in no downtime. Normally, certain types of changes would have involved taking down SAP for at least an hour.

The Southwire team also appreciates the fact that the modern cloud architecture means spending less time on routine infrastructure maintenance. “It’s one less thing for me to worry about,” Stuart says, “I can focus on the business side of the house and move the technology and responsibilities to what we do within the Google Cloud Platform.”

What comes next?

While the cloud migration will increase stability, uptime, performance, and security, there is much more to come. Southwire is currently working on a disaster recovery implementation for their SAP environment on Google Cloud. Stuart and Schleupner are excited about where Google Cloud can further take Southwire. They are considering an SAP Hybris e-commerce implementation as well as connected factory and/or factory automation initiatives that can take advantage of artificial intelligence and machine learning. 

To Stuart and Schleupner, the migration of Southwire’s SAP environment to Google Cloud, as important as it was, really represents the first step in the company’s tech evolution. Now that much of the heavy lifting is complete, Southwire’s digital transformation can begin in earnest. “There’s no shortage of areas where I think Google Cloud will come into play,” Stuart says, “and we intend to look at these things with an open mind to understand how we can leverage current investments to take our organization where we want to go.”

Learn more about Southwire’s SAP on Google Cloud deployment and how Google Cloud can transform the way you work with your SAP enterprise applications. Visit cloud.google.com/solutions/sap.