💧 River Data for Tomorrow, Today

Previous Relevant Presentations

Intoto Islands 🏝

Intoto Beta

Purpose of the Presentation

A look at the tech & "under the hood"

Specific use cases using the tech

Showcase what sets Intoto apart

Our guiding principles

Where we are going

1. Introduction

2. Technical Overview

3. Use Cases

4. Differentiation

5. Security and Scalability

6. Roadmap and Future Plans

7. Achievements and Traction

7. Conclusion (Questions and Discussion

Introduction

Scott Basgaard

CTO and Co-founder @ Intoto

15 Years Professional Web Development

WooCommerce

WordPress VIP

Facebook

Time Inc.

Reader's Digest

Airbnb

Career Log: scottbasgaard.com

🇺🇸 🇳🇴

A Strong and Experienced Team

Benny Thomas

Gaya Kessler

Scott Basgaard

Richard Strømland Egeli

Morten Hauan

Ådne Stokkeland

Sveinung Egeland

Frode Aagedal

Alf Magne M. Versland

Christer Skaar

CTO

Developer

Developer

Developer

COO

Data Scientist

Developer

CEO

Project Manager

Field Engineer

Benny Thomas

Gaya Kessler

Scott Basgaard

Richard Strømland Egeli

Morten Hauan

Ådne Stokkeland

Sveinung Egeland

Frode Aagedal

Alf Magne M. Versland

Christer Skaar

Engaged Problem Solver

Engaged Problem Solver

Engaged Problem Solver

Engaged Problem Solver

Engaged Problem Solver

Engaged Problem Solver

Engaged Problem Solver

Engaged Problem Solver

Engaged Problem Solver

Engaged Problem Solver

Quick Background

1. Introduction

2. Technical Overview

3. Use Cases

4. Differentiation

5. Security and Scalability

6. Roadmap and Future Plans

7. Achievements and Traction

8. Conclusion (Questions and Discussion)

Technical Overview

Quick Analogy

Quick Analogy

Both are the "same" news at the exact time the newspaper is printed.

Both are fundamentally different.

Batch vs. Stream Processing

"Batch processing is a method of processing data in large volumes at once. In this approach, data is collected over a period of time, stored in a database or data warehouse, and then processed in batches. Batch processing is suitable for use cases where the data doesn't need to be processed in real-time and where it's acceptable to have a delay between the data collection and processing.

 

Examples of batch processing use cases include billing, report generation, and data analysis."

- ChatGPT

"Stream processing is a method of processing data in real-time as it is generated. In this approach, data is continuously flowing and being processed as soon as it is generated. Stream processing is suitable for use cases where data needs to be processed in real-time or near real-time.

 

Examples of stream processing use cases include fraud detection, real-time analytics, and monitoring of IoT devices."

- ChatGPT

What is Stream Processing?

- Philipp Brunenberg

Coming from various projects in the big data landscape of German companies I realize that many of the companies are facing similar problems. They have old legacy systems in place that are very good at what they where designed and built for at that time. Today, new technologies arise and new things become possible. 

For example if we process our data only once a day, we have the results of yesterday’s business day available only today.

Intoto is fundamentally different.

Real Time River Data Starts Here

Not Here

Own the stack.

1. Data

1. Data

1. Data

The birth of an Intoto event.

1. Introduction

2. Technical Overview

3. Use Cases

4. Differentiation

5. Security and Scalability

6. Roadmap and Future Plans

7. Achievements and Traction

8. Conclusion (Questions and Discussion)

Use Cases

1. Hydropower

2. Planning and Decision Making

3. Automation

1. Hydropower 

1. Hydropower

Machine Learning

1. Hydropower

1. Hydropower

Input

1. Last 36 hours of Intoto water level at specific location.

2. Last 36 hours of Rainfall from 4 local weather stations (MET).

3. Rainfall forecast from same 4 weather stations.

Output

1. Predicted river height for the next 36 hours.

Current Machine Learning Model

1. Hydropower

Misc.

- Running once an hour on AWS SageMaker

Current Machine Learning Model

1. Hydropower

1. Hydropower

1. Hydropower

Optimizing controlled outlet from dam to follow regulations for minimum flow downstream of dam.

Current Case w/ Client

Uses up to 12 different meteorological parameters.

Case goal is 60 hour prediction of downstream flow based on future setting at dam outlet.

2. Planning and Decision Making

Kristiandsand Kommune

2. Planning and Decision Making

må jeg jo si at systemet har vært til god hjelp i helgen siden vi har hatt en del flom våre elver..

- Beredskapssjef 

2. Planning and Decision Making

2. Planning and Decision Making

2. Planning and Decision Making

3. Automation

3. Automation

Kalking / Liming

1. Introduction

2. Technical Overview

3. Use Cases

4. Differentiation

5. Security and Scalability

6. Roadmap and Future Plans

7. Achievements and Traction

8. Conclusion (Questions and Discussion)

Differentiation

A Platform for River Data

Freedom to Choose

Coming from various projects in the big data landscape of German companies I realize that many of the companies are facing similar problems. They have old legacy systems in place that are very good at what they where designed and built for at that time. Today, new technologies arise and new things become possible. 

1. Introduction

2. Technical Overview

3. Use Cases

4. Differentiation

5. Security and Scalability

6. Roadmap and Future Plans

7. Achievements and Traction

8. Conclusion (Questions and Discussion)

Security and Scalability

Built on

  • Strong focus on security and offers various features to help secure our infrastructure.
  • Utilizing Identity and Access Management (IAM), Virtual Private Cloud (VPC), and AWS Security Hub.
  • Offers compliance certifications like SOC 1, 2 and 3, ISO 27001, HIPAA, and PCI DSS to ensure that our infrastructure meets various regulatory and compliance requirements.

Security

  • Global infrastructure.
  • Pay for what we use.
  • Scale up or down infrastructure as needed to meet the changing demands of our business.
  • AWS offers several pricing models, including on-demand, reserved instances, and spot instances, etc. which help you optimize costs.
  • Proven track record for up-time and offers Service Level Agreements (SLAs) for many of its services.

Scalability

1. Introduction

2. Technical Overview

3. Use Cases

4. Differentiation

5. Security and Scalability

6. Roadmap and Future Plans

7. Achievements and Traction

8. Conclusion (Questions and Discussion)

Roadmap and Future Plans

Introduce Saas Model and Paid Features / Plans

Custom Alert / Alarm Triggers

Real-time Layers and Maps

Integrate w/ Other Data Providers and Break Out of 🇳🇴

Dynamic Machine Learning Models

ChatGPT

More Open Source / Community Driven "Parts"

Other

1. Introduction

2. Technical Overview

3. Use Cases

4. Differentiation

5. Security and Scalability

6. Roadmap and Future Plans

7. Achievements and Traction

8. Conclusion (Questions and Discussion)

Achievements and Traction

1. Introduction

2. Technical Overview

3. Use Cases

4. Differentiation

5. Security and Scalability

6. Roadmap and Future Plans

7. Achievements and Traction

8. Conclusion (Questions and Discussion)

Questions & Discussion

1. Introduction

2. Technical Overview

3. Use Cases

4. Differentiation

5. Security and Scalability

6. Roadmap and Future Plans

7. Achievements and Traction

8. Conclusion (Questions and Discussion)

Made with Slides.com