AI Approaches to Optimize Grid Effectiveness

OVERVIEW

Midcontinent Independent Systems Operator (MISO), the Seeker for this Wazoku Crowd Challenge, is looking for comprehensive AI-based approaches that would assist in increasing the effectiveness, reliability, and efficiency of the electric grid.

In North America, MISO generates, transmits, and distributes electric energy to millions of consumers. This Challenge is designed to gather and award proposals for how to leverage the unique capabilities of Artificial Intelligence (AI) tools, methods, and approaches in order to innovate and lead the sector.

Solvers are encouraged to provide detailed descriptions of AI-based solutions across different use cases which could feasibly increase the reliability, effectiveness, and economic efficiency of the grid and its operations.
 

By taking part in this Prize Challenge you are granting MISO a right to use (but not own) your submitted information, however MISO must determine award winners within 45 days from the start of evaluation, otherwise MISO loses this right.
 

This Prize Challenge requires a written proposal to be submitted and the total guaranteed award of $15,000 USD will be paid, with awards to at least one submitted solution. There is no assignment of IP Rights with this challenge.

In this Prize Challenge, Solvers may:

• Submit ideas of their own
• Submit third-party information that they have the right to use and further, the authority to convey MISO this right with the right to use and develop derivative works
• Submit information considered in the public domain without any limitations on use

Submissions to this Challenge must be received by 11:59 PM (US Eastern Time) on September 24th, 2024.

- Login or register your interest to start solving!

ABOUT THE SEEKER & ELIGIBILITY

Midcontinent Independent System Operator (MISO) is an independent, not-for-profit organization that delivers safe, cost-effective electric power across 15 U.S. states and the Canadian province of Manitoba. Operating one of the world’s largest energy markets (with annual energy transactions worth more than $29 billion), MISO is committed to collaborating with all stakeholders to create cost-effective and innovative solutions for our changing industry. To learn more about MISO and its mission, visit www.misoenergy.org  and read about its Strategy and Value Proposition.

Employees of ­­­­Midcontinent Independent System Operator (MISO) and their families are not eligible to receive awards for this Challenge.

Any individual or entity, located in or associated with any country, region, or government that is subject to sanctions or embargoes imposed by the United States government, is not eligible to receive award payments in relation to this Challenge.

Find out more about participation in Wazoku Crowd Challenges.

THE CHALLENGE

Background

Within MISO, various teams, individuals, and processes are leveraging AI to improve productivity and problem-solving. The productivity and effectiveness achieved at the single-point level has directly informed this Wazoku Crowd Challenge.

Solvers are asked for ideas, solutions, and technologies that leverage complex, multi-phase AI-based approaches to innovate MISO’s grid operations. These could consist of ideas for use cases, generative AI applications, large language model (LLM) tools, computer vision uses, custom AI-based platforms or products, or any other AI-based approach that goes beyond simply machine learning and achieves increased effectiveness of grid operations.

MISO operations encompass the lifecycle of energy across the grid. MISO facilities and operators are responsible for generating electricity, transmitting it across the continent, buying and selling to stakeholders, and then distributing it to the point of consumption for commercial, residential, and industrial customers. The different areas of grid generation, transmission, and distribution of particular interest to MISO with regards to AI approaches include reliable operation of the transmission system, more efficient energy markets, network planning, and generation outages.

MISO is at the forefront of reliably and efficiently delivering electricity to millions of people across North America. The breadth and depth of its grid operations provide ideal use cases for the application of novel, complex AI approaches. AI tools, approaches, and methods could unlock further speed, efficiency, and processing power which would increase the effectiveness of MISO’s activities.

The Challenge

The goal of this Challenge is for Solvers to provide well-reasoned ideas and approaches that identify opportunities within areas of interest and propose AI-based solutions and use cases that could address the multi-faceted issues faced by the electric grid and its operators.

In order to understand how to optimize the grid’s operations with AI, it is important to outline the areas of particular interest. MISO’s desired applications of complex, multi-stage AI-based approaches from Solvers could be applied to, but are not limited to:

Renewable Integrations

Optimizing the integration of renewable energy sources (e.g. wind, solar, geothermal) into the electric power transmission system is an ongoing challenge across the grid.

The variability in power produced by weather condition-dependent sources like wind farms and solar panels makes predictability of these assets complicated. Not knowing how much energy to expect and when can lead to unexpected drops or surges, complicating grid management and load balancing activities for operators such as MISO.

In order to generate large amounts of energy, renewable energy generation farms are often located far from urban centers – where there is enough space to achieve ideal generation. However, because this is often far from where the energy is needed, this requires significant transmission infrastructure and management to reliably deliver power to end customers.

Flexibility and Stability

Particularly relevant due to the integration of renewable assets, increasing our ability to maintain the stability of the energy grid with AI-based solutions would lead to greater consistency of service to all customers.

This could take the form of demand forecasting (and responsive, dynamic balancing and resulting load management), optimization of distribution according to need, and improved stability and security of the regional grids that make up MISO’s operations.

Prediction/Forecasting Load Changes

Using AI to forecast future demand, including from distributed energy resources (known collectively as Behind-the-Meter or BTM generation), would improve the effectiveness of predictive generators.
 

With the rise of cryptocurrency mining, which constitutes 0.6-2.3% of U.S. electricity consumption every year (data from U.S. Energy Information Administration), the grid is under greater demands with every year. The rise of data centers also contribute to an increased load which must be matched with smarter, better supported prediction and monitoring in order to ensure good service.

MISO also works in concert with other operators and interdependent infrastructure to plan outages, in order to mitigate problems that could occur. AI-based approaches could help to better coordinate the management and impact of these necessary maintenance outages.

Being able to better predict the needs of the grid through validated data and AI insights would improve performance across the MISO-operated grid.

Cybersecurity and Risk

Across the world, energy grids are a key target for bad actors and cyber attacks. An August 2023 report from the International Energy Agency revealed that cyberattacks against utilities doubled between 2020 and 2022, with an average incident cost of a data breach costing US$4.72m in the energy sector.

Keeping consumer data, grid controls, and energy consumption safe from malicious attacks is a core priority for MISO and other grid operators. Using complex, multi-phase AI approaches to support cybersecurity (whether in prediction, detection, or prevention) would help to safeguard core energy infrastructure.

Additionally, AI can be used to great effect on pattern-matching and predictions: with one area of relevance to MISO being cyber risk maturity outcome patterns.

Compliance and Incident Management

MISO is an independent system operator formed under the authority of the U.S. Federal Energy Regulatory Commission (FERC). The North American Electric Reliability Corporation (NERC) is a not-for-profit international regulatory authority whose mission is to assure the effective and efficient reduction of risks to the reliability and security of the grid. NERC develops and enforces Reliability Standards to which MISO is subject. In addition, MISO has specific incident management teams and procedures related to maintaining reliable grid operations during incidents involving weather, security, human resources, facilities etc. in varying levels of severity.

AI tools can assist large and complex organizations like MISO by automating the monitoring and reporting of potential compliance breaches and incidents. By leveraging multi-phase AI approaches, MISO hopes that Solvers can help to unlock early warning systems for potential incidents, predefined responses to mitigate any risk, and relevant process automation to reduce risks of natural human error or oversight.

Customer-based approaches

With diverse consumers – from those using the grid’s electricity in their homes, through to commercial and industrial applications of power – MISO has vast datasets on behavior, investments, operation, and application of energy produced by grid assets.

AI could analyze, predict, and suggest changes in order to optimize future load distribution and generation needs.

Solvers are encouraged to submit detailed descriptions of their AI-based approach, showing its potential clear and measurable impact on the effectiveness of grid operations and how it goes beyond single-phase or solely algorithm-based approaches.

MISO welcomes the art of the possible within your solutions, however please note: any solution must be feasible within MISO’s operational context and use cases. Solvers have free rein to suggest solutions that meet the guideline solution requirements, so long as they are detailed, effective, go beyond single-point solutions, and are appropriate for use with complex grid management activities.

SOLUTION REQUIREMENTS

MISO is primarily interested in solutions with the potential to meet the following requirements:

Must have:

1. Solution shows rationale for clear and measurable improvement in effectiveness of one or more aspects of electric grid operations
   • Please be specific in your use case(s)/area(s) of application for the AI-based approach, including how the solution addresses the identified problem or opportunity.
   • This could relate to any of the activities relating to the generation, transmission, distribution, or management of electric energy by MISO and its operators.
2. Solution leverages Artificial Intelligence (AI) approaches, tools, and/or methods
   • Any AI-based technology, approach, or method detailed in your submission must be more complex than simple machine learning or predictive algorithms.

Nice to have:

1. MISO welcomes Solvers’ solutions with further detail to bolster their submission, including but not limited to: validated datasets, end-to-end program designs, scripts, or custom software.
   
   Any additional detail would be favored when MISO determines award breakdown following theoretical evaluation.

Things to Avoid:

Please note: MISO is not interested in pure machine learning (ML) or predictive algorithm ideas for using AI. MISO is unlikely to award any solutions that rely solely on interpretation and processing of large datasets without giving recommendations for how that AI approach will bring significant impacts on grid effectiveness.

Solutions with Technology Readiness Levels (TRLs) 1-9 are invited, ideation to consider WHAT to do; proof of concept solutions that propose HOW to solve the specific solution requirements; or production ready collaboration proposals about existing technologies and/or WHO can provide these.

This Prize Challenge has the following features:
 

1. By taking part in this Prize Challenge you are granting Midcontinent Independent System Operator (MISO) a right to use (but not own) your submitted information, however MISO must determine the award winners within 45 days from the start of evaluation, otherwise MISO loses this right. You will receive notification.

2. There will be a guaranteed award of $15,000, with at least one award being no smaller than $5,000 and no award being smaller than $2,500.

3. The award distribution will be determined after theoretical evaluation of the proposals by MISO.

4. Solvers may:

• Submit ideas of their own
• Submit third-party information that they have the right to use and further, the authority to convey to MISO this right with the right to use and develop derivative works
• Submit information considered in the public domain without any limitations on use

5. MISO may also issue “Honorable Mention” recognitions for notable submissions that are not selected for monetary awards.

YOUR SUBMISSION

Please login and register your interest, to complete the submission form.

The submitted proposals must be written in English and can include:

1. Participation Type – you will first be asked to inform us how you are participating in this challenge, as a Solver (Individual) or Solver (Organization).
2. Solution Level - the Technology Readiness Level (TRL) of your solution.
3. Problem & Opportunity - highlight the innovation in your approach to the Problem, its point of difference, and the specific advantages/benefits this brings (up to 500 words).
4. Solution Overview - detail the features of your solution and how they address the SOLUTION REQUIREMENTS (500 words, there is space to add more in the summary field, and attach supporting data, diagrams, etc).
5. Experience - Expertise, use cases and skills you or your organization have in relation to your proposed solution.  (up to 500 words).
6. Solution Risks - any risks you see with your solution and how you would plan for this (up to 500 words).
7. Timeline, capability and costs - describe what you think is required to deliver the solution, estimated time and cost (up to 500 words).
8. Online References - provide links to any publications, articles or press releases of relevance (up to 500 words).

Wazoku encourages the use by Solvers of AI approaches to help develop their submissions, though any produced solely with generative AI are not of interest.

Find out more about participation in Wazoku Crowd Challenges.

Submissions to this Challenge must be received by 11:59 PM (US Eastern Time) on September 24th, 2024.

Late submissions will not be considered.

Your submission will be evaluated by the evaluation team first reviewing the information and content you have submitted at the submission form, with attachments used as additional context to your form submission. Submissions relying solely on attachments will receive less attention from the evaluation team.

After the Challenge submission due date, MISO will complete the review process and make a decision with regards to the winning solution(s) according to the timeline in the Challenge header. All Solvers who submit a proposal will be notified about the status of their submissions.