How dida Automates Sales Processes with Mathematics and Machine Learning
Customer Company Size
Large Corporate
Region
- Europe
Country
- Germany
Product
- Google Cloud
- Google Maps Platform API
- Compute Engine
- TensorBoard
- Vertex AI
Tech Stack
- Machine Learning
- CI/CD pipeline
- Projective Geometry
- Google Cloud Storage
- GPUs
Implementation Scale
- Enterprise-wide Deployment
Impact Metrics
- Productivity Improvements
- Cost Savings
- Customer Satisfaction
Technology Category
- Analytics & Modeling - Machine Learning
- Application Infrastructure & Middleware - Data Exchange & Integration
- Platform as a Service (PaaS) - Data Management Platforms
Applicable Industries
- Renewable Energy
- Software
Applicable Functions
- Sales & Marketing
- Business Operation
Use Cases
- Predictive Maintenance
- Process Control & Optimization
- Remote Asset Management
Services
- Software Design & Engineering Services
- System Integration
About The Customer
Enpal is a leading greentech company in Germany, known for its innovative approach to providing solar energy solutions. As the first greentech unicorn in the country, Enpal has been experiencing rapid growth due to the rising demand for environmental sustainability solutions. The company specializes in offering solar panel installations to residential customers, aiming to make renewable energy accessible and affordable. Enpal's commitment to sustainability and innovation has positioned it as a key player in the renewable energy sector, driving the transition towards a greener future.
The Challenge
Enpal, a rapidly growing greentech company in Germany, faced challenges in scaling its solar panel sales process. The traditional method involved manually estimating roof angles and counting roof tiles, which was time-consuming and error-prone. This process took 120 minutes per customer, making it difficult to keep up with the increasing demand for solar panels. Enpal needed a more efficient and accurate solution to generate quotes for prospective customers, which led them to seek a custom AI solution to automate the process.
The Solution
Dida developed a custom AI solution for Enpal using Google Cloud's platform. The solution involved breaking down the sales process into smaller, modular steps, allowing for a more explainable and efficient system. Google Maps Platform API was used to gather rooftop images, which were stored in Cloud Storage. A machine learning model was trained to distinguish rooftops and calculate roof angles using projective geometry. Compute Engine with GPUs was utilized to accelerate the model training process, and TensorBoard was used to monitor the training. The final solution automated the calculation of roof size and solar panel requirements, significantly reducing the time and errors associated with the manual process.
Operational Impact
Quantitative Benefit
Case Study missing?
Start adding your own!
Register with your work email and create a new case study profile for your business.
Related Case Studies.
Case Study
Remote Monitoring & Predictive Maintenance App for a Solar Energy System
The maintenance & tracking of various modules was an overhead for the customer due to the huge labor costs involved. Being an advanced solar solutions provider, they wanted to ensure early detection of issues and provide the best-in-class customer experience. Hence they wanted to automate the whole process.
Case Study
Vestas: Turning Climate into Capital with Big Data
Making wind a reliable source of energy depends greatly on the placement of the wind turbines used to produce electricity. Turbulence is a significant factor as it strains turbine components, making them more likely to fail. Vestas wanted to pinpoint the optimal location for wind turbines to maximize power generation and reduce energy costs.
Case Study
Siemens Wind Power
Wind provides clean, renewable energy. The core concept is simple: wind turbines spin blades to generate power. However, today's systems are anything but simple. Modern wind turbines have blades that sweep a 120 meter circle, cost more than 1 million dollars and generate multiple megawatts of power. Each turbine may include up to 1,000 sensors and actuators – integrating strain gages, bearing monitors and power conditioning technology. The turbine can control blade speed and power generation by altering the blade pitch and power extraction. Controlling the turbine is a sophisticated job requiring many cooperating processors closing high-speed loops and implementing intelligent monitoring and optimization algorithms. But the real challenge is integrating these turbines so that they work together. A wind farm may include hundreds of turbines. They are often installed in difficult-to-access locations at sea. The farm must implement a fundamentally and truly distributed control system. Like all power systems, the goal of the farm is to match generation to load. A farm with hundreds of turbines must optimize that load by balancing the loading and generation across a wide geography. Wind, of course, is dynamic. Almost every picture of a wind farm shows a calm sea and a setting sun. But things get challenging when a storm goes through the wind farm. In a storm, the control system must decide how to take energy out of gusts to generate constant power. It must intelligently balance load across many turbines. And a critical consideration is the loading and potential damage to a half-billion-dollar installed asset. This is no environment for a slow or undependable control system. Reliability and performance are crucial.
Case Study
Remote Monitoring and Control for a Windmill Generator
As concerns over global warming continue to grow, green technologies are becoming increasingly popular. Wind turbine companies provide an excellent alternative to burning fossil fuels by harnessing kinetic energy from the wind and converting it into electricity. A typical wind farm may include over 80 wind turbines so efficient and reliable networks to manage and control these installations are imperative. Each wind turbine includes a generator and a variety of serial components such as a water cooler, high voltage transformer, ultrasonic wind sensors, yaw gear, blade bearing, pitch cylinder, and hub controller. All of these components are controlled by a PLC and communicate with the ground host. Due to the total integration of these devices into an Ethernet network, one of our customers in the wind turbine industry needed a serial-to-Ethernet solution that can operate reliably for years without interruption.
Case Study
Temperature monitoring for vaccine fridges
Dulas wanted a way to improve the reliability of the cold chain, facilitating maintenance and ensuring fewer vaccines are spoiled. Dulas wanted an M2M solution which would enable them to record and report the temperature inside vaccine refrigerators.
Case Study
IoT Powering A New Way to Light Streets with Bifacial Solar Panels
When James Meringer’s commercial contracting business experienced a rapid increase in solar projects, he also saw an opportunity to extend the benefits of solar by using the bifacial solar panels he’d become familiar with in new ways. Bifacial solar panels enable sunlight from both sides of the panel, making it a more efficient harvest of solar power. Seeing the panel’s power, James and his team set out to use the same technology for street lighting. Until now, solar street lights have served as utilitarian solutions that force designers to choose between form and function. The Mira Bella Energy team has changed that.
