FlexEVility

AI Quick Summary

One Liner: FlexEVility provides a predictive energy management platform designed to optimise energy procurement for schedule-driven electric vehicle fleets. This platform offers a means of reducing significant risks in energy procurement, costs and facilitating efficient fleet electrification. The flexEVility PlatformStatus Quo:Countries around the world have established countermeasures against climate change, primarily focusing on the reduction of greenhouse gas emissions. Switzerland's Energy Strategy 2050 aims to decarbonize various sectors, including mobility. Battery electric vehicles (BEVs) are currently the most viable solution for decarbonizing transportation, particularly for large fleet operators. However, transitioning to an electrified fleet poses significant challenges and uncertainties.Problem:Traditionally, diesel-powered trucks and buses operated continuously throughout the day, refueling only at the end of their shifts. This straightforward refueling process did not require detailed energy consumption measurements. With the shift to electric fleets, fleet operators now face complexities in estimating the energy required for recharging. The procurement of electric energy, a critical component of operational costs, will become a focal point of their operation.Energy is typically procured through energy trading agencies or as part of a utility company’s services. This process involves creating a load profile for the fleet to estimate energy needs. However, these profiles are not known in detail. Therefore, the energy trading agencies have to hedge against potential over- or underestimation of energy demand. Hence, the uncertainty in these profiles results in higher risk margins, leading to increased costs. Contracts for energy procurement are often set years in advance, making it challenging to accurately predict future energy demands, especially during the transition to electric vehicles. This leads directly to two problems.Short-Term Problem:During the gradual transition to an electric fleet, fleet operators introduce 10–20 additional electric vehicles annually. This incremental change makes it difficult to account for the rising electric energy demand in these long-term energy contracts, leading to high-risk margins and increased electricity prices. This can unnecessarily inflate overall costs and potentially slow down the transition to electric fleets.Long-Term Problem:Once fully electrified, the fleet's total daily electric energy demand becomes a significant operational cost. Due to the high volume of energy required, even small inaccuracies in demand prediction can result in substantial risk premiums on the procured energy. Both the uncertainty during the transition and the subsequent operation of a fully electrified fleet are cost-intensive, especially for operators in competitive environments or those mandated to reduce costs, such as public bus companies.Solution:Our solution centers on providing precise demand foresight using a holistic physical model tailored to the fleet operator's schedule-driven operations. Conventional load prediction models concentrate on forecasting the energy consumption of municipalities or comparable entities and hence must rely on the utilisation of statistical techniques and inherent uncertain machine learning if consumption data is inaccurate. Our approach has been to select a consumer group whose energy consumption patterns are largely predictable due to their adherence to specific timetables, which are planned well in advance. Our model integrates detailed vehicle data, route features, and their specific timetables. This allows for precise forecasting of the fleet's electric demand, aiding in both long-term energy procurement and short-term operational adjustments.Additionally, during day-to-day operations, our model validates consumption and identifies deviations in energy demand days ahead. This advanced knowledge allows for optimized energy procurement, reducing the need for risk margins. In the event of any deviations, there is sufficient time to react accordingly. The aim is to purchase the exact amount of energy at the lowest possible tariffs in the day-ahead market. In any case, high balancing costs can be mitigated through accurate predictions of the delivered energy.Environmental Impact:The flexEVility platform implicitly supports CO₂ reduction by facilitating the transition to electric vehicles, aiding fleet operators in achieving their climate targets more efficiently. By leveraging the higher efficiency of electric drive systems, the overall primary energy needed for mobility can be lowered and energy independence can be enhanced. Additionally, the accelerated adoption of electric utility vehicles drives broader expansion of electromobility, benefiting from scaling effects. Moreover, the enhanced understanding of the fleet's energy requirements can be leveraged in prospective energy flexibility markets to bolster the power grid and potentially defer or avert costly grid expansions, as well as the directly associated CO₂ emissions.Customer Base:Our precise forecasting algorithm, which relies on time and route-based schedules, is applicable to all schedule-driven fleet operators. This includes public bus transportation, delivery services with fixed schedules, and railroad traffic. On-demand delivery services are currently excluded from our solution, as their nature leads to spontaneous and hardly predictable operation.Additional Revenue Streams:In the energy sector, flexibility and grid stability services are key revenue streams that require real-time prediction of energy demand and significant hardware infrastructure to operate the necessary flexible assets accordingly. Our solution addresses a previously unaddressed area with a lower technical barrier, , namely the energy procurement and forecasting process. The digital twin we build offers real-time and long-term energy forecasts for entire fleets, leveraging operator-specific data and advanced computational capabilities.However, as soon as we establish a reliable forecasting service and build customer trust, we can explore additional consulting and implementation services. Hereby, we will tap into the markets associated with flexibility services and grid stability. The then already existing charging infrastructure can be integrated into our solution using defined interfaces, eliminating the need for proprietary charging stations. The approach, to first solve a procurement problem and then scale into the upcoming markets allows for early revenue generation and scalability across various services.Milestones & Use of Funds:Demonstration of Advantage:We need to acquire a dataset from energy traders representing their standard procurement product to compare against our enriched procurement methodology. This involves obtaining their applied price curve for a specific period (e.g., 2023) and operation schedules, which we can source from coop.Host First MVP and Build Online Presence:Our current Minimum Viable Product (MVP) is available locally. To demonstrate the solution live, we plan to host the MVP online to showcase its capabilities to potential customers. Additionally, we will establish a website to publish results, offer a reduced form of the MVP for trial, and function as a knowledge hub for the services we provide.Workshop Organization:We will organize a workshop to gather extensive feedback on our platform, aiming to enhance its usability and develop it into a marketable product. The workshop will also serve as a networking opportunity with potential clients and stakeholders.Innobooster Network:Leveraging the booster program's network will provide critical reviews and insights, helping us identify areas for improvement and further development of our solution.

Project Idea Metadata

• Project Idea Name: FlexEVility
• Date: 8/20/2024 6:48:40 AM
• Administrators:
  • Florian Kühlkamp

Project Idea Description

The flexEVility Platform

Status Quo:

Countries around the world have established countermeasures against climate change, primarily focusing on the reduction of greenhouse gas emissions. Switzerland's Energy Strategy 2050 aims to decarbonize various sectors, including mobility. Battery electric vehicles (BEVs) are currently the most viable solution for decarbonizing transportation, particularly for large fleet operators. However, transitioning to an electrified fleet poses significant challenges and uncertainties.

Problem:

Traditionally, diesel-powered trucks and buses operated continuously throughout the day, refueling only at the end of their shifts. This straightforward refueling process did not require detailed energy consumption measurements. With the shift to electric fleets, fleet operators now face complexities in estimating the energy required for recharging. The procurement of electric energy, a critical component of operational costs, will become a focal point of their operation.

Energy is typically procured through energy trading agencies or as part of a utility company’s services. This process involves creating a load profile for the fleet to estimate energy needs. However, these profiles are not known in detail. Therefore, the energy trading agencies have to hedge against potential over- or underestimation of energy demand. Hence, the uncertainty in these profiles results in higher risk margins, leading to increased costs. Contracts for energy procurement are often set years in advance, making it challenging to accurately predict future energy demands, especially during the transition to electric vehicles. This leads directly to two problems.

Short-Term Problem:

During the gradual transition to an electric fleet, fleet operators introduce 10–20 additional electric vehicles annually. This incremental change makes it difficult to account for the rising electric energy demand in these long-term energy contracts, leading to high-risk margins and increased electricity prices. This can unnecessarily inflate overall costs and potentially slow down the transition to electric fleets.

Long-Term Problem:

Once fully electrified, the fleet's total daily electric energy demand becomes a significant operational cost. Due to the high volume of energy required, even small inaccuracies in demand prediction can result in substantial risk premiums on the procured energy. Both the uncertainty during the transition and the subsequent operation of a fully electrified fleet are cost-intensive, especially for operators in competitive environments or those mandated to reduce costs, such as public bus companies.

Solution:

Our solution centers on providing precise demand foresight using a holistic physical model tailored to the fleet operator's schedule-driven operations. Conventional load prediction models concentrate on forecasting the energy consumption of municipalities or comparable entities and hence must rely on the utilisation of statistical techniques and inherent uncertain machine learning if consumption data is inaccurate. Our approach has been to select a consumer group whose energy consumption patterns are largely predictable due to their adherence to specific timetables, which are planned well in advance. Our model integrates detailed vehicle data, route features, and their specific timetables. This allows for precise forecasting of the fleet's electric demand, aiding in both long-term energy procurement and short-term operational adjustments.

Additionally, during day-to-day operations, our model validates consumption and identifies deviations in energy demand days ahead. This advanced knowledge allows for optimized energy procurement, reducing the need for risk margins. In the event of any deviations, there is sufficient time to react accordingly. The aim is to purchase the exact amount of energy at the lowest possible tariffs in the day-ahead market. In any case, high balancing costs can be mitigated through accurate predictions of the delivered energy.

Environmental Impact:

The flexEVility platform implicitly supports CO₂ reduction by facilitating the transition to electric vehicles, aiding fleet operators in achieving their climate targets more efficiently. By leveraging the higher efficiency of electric drive systems, the overall primary energy needed for mobility can be lowered and energy independence can be enhanced. Additionally, the accelerated adoption of electric utility vehicles drives broader expansion of electromobility, benefiting from scaling effects. Moreover, the enhanced understanding of the fleet's energy requirements can be leveraged in prospective energy flexibility markets to bolster the power grid and potentially defer or avert costly grid expansions, as well as the directly associated CO₂ emissions.

Customer Base:

Our precise forecasting algorithm, which relies on time and route-based schedules, is applicable to all schedule-driven fleet operators. This includes public bus transportation, delivery services with fixed schedules, and railroad traffic. On-demand delivery services are currently excluded from our solution, as their nature leads to spontaneous and hardly predictable operation.

Additional Revenue Streams:

In the energy sector, flexibility and grid stability services are key revenue streams that require real-time prediction of energy demand and significant hardware infrastructure to operate the necessary flexible assets accordingly. Our solution addresses a previously unaddressed area with a lower technical barrier, , namely the energy procurement and forecasting process. The digital twin we build offers real-time and long-term energy forecasts for entire fleets, leveraging operator-specific data and advanced computational capabilities.

However, as soon as we establish a reliable forecasting service and build customer trust, we can explore additional consulting and implementation services. Hereby, we will tap into the markets associated with flexibility services and grid stability. The then already existing charging infrastructure can be integrated into our solution using defined interfaces, eliminating the need for proprietary charging stations. The approach, to first solve a procurement problem and then scale into the upcoming markets allows for early revenue generation and scalability across various services.

Milestones & Use of Funds:

Demonstration of Advantage:

We need to acquire a dataset from energy traders representing their standard procurement product to compare against our enriched procurement methodology. This involves obtaining their applied price curve for a specific period (e.g., 2023) and operation schedules, which we can source from coop.

Host First MVP and Build Online Presence:

Our current Minimum Viable Product (MVP) is available locally. To demonstrate the solution live, we plan to host the MVP online to showcase its capabilities to potential customers. Additionally, we will establish a website to publish results, offer a reduced form of the MVP for trial, and function as a knowledge hub for the services we provide.

Workshop Organization:

We will organize a workshop to gather extensive feedback on our platform, aiming to enhance its usability and develop it into a marketable product. The workshop will also serve as a networking opportunity with potential clients and stakeholders.

Innobooster Network:

Leveraging the booster program's network will provide critical reviews and insights, helping us identify areas for improvement and further development of our solution.

One Liner:

FlexEVility provides a predictive energy management platform designed to optimise energy procurement for schedule-driven electric vehicle fleets. This platform offers a means of reducing significant risks in energy procurement, costs and facilitating efficient fleet electrification.