by Nada Welker | Nov 30, 2022 | Automotive Industry, Future Trends, New Mobility, Smart City
Fully autonomous vehicles are still rarely encountered on public roads, although autonomous driving has long since ceased to be mere dreams of the future. The legal framework for fully autonomous vehicles is in place: the “Automated Driving Act”, which has already been in force in Germany for level 3 vehicles since 2017, was extended to include level 4 autonomous vehicles in July 2021 by the German Government. Autonomous vehicles are classified in several levels: Levels 0-2 denote the classic self-driving vehicle, which in some cases already receives automated support from the vehicle (from Level 2), for example, through a lane departure warning system. Level 3 marks the beginning of highly automated driving, in which the vehicle can already take on certain tasks (such as highway driving) independently. In level 4, driving is fully automated and an active driver is no longer necessary. The vehicle then becomes fully autonomous in stage 5.
The slow progress in the entry of autonomous vehicles into road traffic is due both to the complexity of the artificial intelligence used in these vehicles and to the high safety requirements they must meet. In order to sufficiently and reliably test software systems of autonomous vehicles, conventional test methods such as test drives are no longer sufficient: They take too long and are too imprecise.
Franz Wotawa from the Institute for Software Technology at TU Graz, explains:
“Autonomous vehicles would have to be driven around 200 million kilometers to prove their reliability – especially for accident scenarios. That’s 10,000 times more test kilometers than are required for conventional cars.”
Wotawa’s research team, which is addressing the safety assurance challenges required for autonomous vehicles, has explored a more efficient testing approach: simulating driving environments using ontologies.
Ontologies for the automatic generation of test scenarios
In Artificial Intelligence, ontologies represent knowledge bases that provide intelligent information systems with relevant information about a specific application domain, on the basis of which they make decisions. This knowledge includes, among other things, entities, i.e., uniquely definable and delimitable units, their behaviors and relationships to each other. Rules and constraints may also be explicitly defined. Transferred to the field of autonomous vehicles, ontologies thus enable intelligent vehicles to understand their driving environment, which is essential for the predictive and risk-minimizing behavior of vehicles in traffic. To this end, the ontologies are fed, for example, with information about the structure of roads, about road users or traffic control elements such as traffic lights. Based on this information, algorithms can generate a multiple of simulations to test the behavior of autonomous vehicles in these scenarios.
Ontology-based testing is faster and more reliable
With the help of ontologies, not only can countless simulation scenarios be generated and tested in a very short time, but also those that are very difficult to reproduce or that humans themselves do not even think of. In a generated test scenario around Wotawa’s team, for example, it was determined that a brake assistance system had not simultaneously detected people approaching the vehicle from different directions and initiated a braking maneuver that would have resulted in one person being injured.
“We have uncovered serious weaknesses in automated driving functions in initial experimental tests. Without these automatically generated simulation scenarios, the weak points would not have been identified so quickly: 9 out of 319 test cases examined resulted in accidents.“ (Franz Wotawa)
Thus, with an ontology-based approach, security vulnerabilities of autonomous vehicles can be detected and patched faster.
Deception of autonomous vehicles
Meanwhile, an example from the U.S. shows a very different risk of autonomous systems: Researchers modified a traffic sign for a speed limit of 80km/h using a patch pattern so that an intelligent sign recognition system would interpret sign as a stop sign. In a public road scenario, the autonomous vehicle would stop abruptly and possibly cause a rear-end collision. The researchers tested several such examples first in a simulation and then in real driving environments. In 90% of the test cases, the traffic signs were actually misinterpreted. Even the smallest changes in the environment can therefore lead to misinterpretations on the part of autonomous systems.
Verifiability as a further prerequisite for the safety of autonomous vehicles
Researchers agree that autonomous vehicles urgently need to be trained to deal with such “manipulations,” whether they are intentional or not. After all, even after autonomous vehicles become established on the road, they will need to continue to learn. Ontology-based simulations should also consider such risky scenarios and verify that autonomous systems are able to correct themselves and make the right decision despite unknown changes in the environment. The German Federal Office for Information Security wants to advocate harmonized guidelines that not only define standards for the development of autonomous vehicles, but also for their verifiability so that their behavior can be tracked. But what is the current legal situation regarding the use of AI in the EU?
EU guidelines strive for excellence and trust
In its Feb. 19, 2020, White Paper on AI, the European Commission committed to promoting the adoption of AI and formulating uniform guidelines for AI-based applications, taking into account safety-critical and ethical aspects. Meanwhile, the Commission has presented a proposal for the world’s first regulatory framework for AI. The regulation proposes to classify AI systems into four risk groups: minimal, low, high and unacceptable.
Autonomous vehicles that make decisions about people’s lives in critical cases are classified as high-risk AI systems. These systems are subject to particularly strict requirements with regard to their development and their documentation:
- A high quality of the data records fed into the system is required to keep risks as low as possible.
- Operations must be logged to enable traceability of results.
- Detailed documentation is a prerequisite for assessing the system’s compliance.
- Adequate risk assessment and mitigation systems must be in place.
- Clear and adequate information must be provided to the user.
- The system should be under adequate human supervision to minimize risks.
- A high level of robustness, security, and accuracy must be provided.
It is currently unclear when the regulation will actually come into force. Currently, it is being discussed in the European Parliament and the European Council.
Magility’s view on the challenges of using ontologies in autonomous vehicles and their testing
Ontology-based testing, due to its ability to automatically generate a wide variety of traffic scenarios, offers a promising approach that could finally accelerate the safe deployment of autonomous vehicles on the road. However, as long as no harmonized regulations apply, manufacturers will find it difficult to ensure the long-term conformity of their vehicles. Legislators are lagging behind the rapidly advancing development and thus the constantly added new possibilities and technologies of AI in automotive applications. Directives must not only be put into force as quickly as possible, but must also be evaluated at appropriate intervals to ensure that they are up to date. In the case of the regulation presented so far, the European Commission envisages the first review only after three years – the need for new urgent safety standards could already arise at much shorter intervals.
Meanwhile, society is still skeptical about fully autonomous driving. A recent study showed that US (19%), German (18%), French and British (17%) customers are the least enthusiastic when it comes to the adoption of autonomous driving.
„Any technological innovation can only be as successful as the social acceptance behind it.“
(Dr. Nari Kahle, Young Global Leader and Head of Strategic Programs at Volkswagen’s software company Cariad)
The extent to which tests based on ontologies can positively influence the lack of trust in autonomous vehicles by society in terms of their potential for guaranteed safety of autonomous vehicles or the EU legal framework remains exciting. Manufacturers will ultimately have to prove that autonomous driving is safer than humans at the wheel and that the number of road accidents can be increasingly reduced by autonomous driving.
At magility, we continue to closely follow the progress of autonomous mobility and keep you up to date on the latest developments. Feel free to contact our experts at magility for an exchange on this topic!
[infobox headline=”At a glance”]
- Ontologies offer an innovative approach to test the safety of autonomous vehicles compared to conventional test methods.
- Based on information such as road conditions, road users and traffic lights, ontologies can describe the driving environments of autonomous vehicles.
- With ontologies, more test scenarios can be generated faster. Rare accident scenarios that are difficult to reproduce can also be run more reliably.
- The European Commission is committed to promoting the adoption of AI and ensuring an excellent level of safety and trust in its use.
- A Commission draft of the world’s first regulatory framework for AI is available. Autonomous vehicles are considered high-risk systems and are subject to special requirements regarding development and documentation.
- Creating social trust in autonomous vehicles is becoming an additional challenge for manufacturers.
[/infobox]
by Julia Riemer | Sep 14, 2022 | Interviews, Know-How and inspiration, Market development & Trends, New Mobility, Smart City, Technologies for new markets
With technological progress, the demand for electrical energy is increasing immensely, making not only generation but also distribution a challenge. This growing demand increases the complexity of power grids as requirements for reliability, efficiency, safety, and environmental and energy compatibility increase. These circumstances require an intelligent grid, now known as the “smart grid.” This is a technology in which intelligent functions are implemented to make the power distribution system more efficient, reliable, and sustainable. This article provides an overview of “smart grids” with its features and application scenarios. Read in the following why smart grids are becoming increasingly important and what solutions are already on the market.
The International Energy Agency (IEA), headquartered in Paris, cites grid integration as one of the four biggest challenges in expanding renewable energy capacity, along with the non-technical challenges of financing, permitting and social acceptance.
By 2026, renewables could grow 60% faster than in the past five years, as the technology to harness wind and solar power has matured and 137 countries have pledged to reduce their fossil fuel power generation to zero. But for the promises to become reality, we need smart grids so that this energy generation and, above all, energy distribution can function properly.
Smart grids perform four important tasks for the energy transition: They increase the resilience of the grid, increase the integration of renewable energies, reduce costs and enable universal access to clean electricity.
What makes smart grids so special?
The constantly increasing demand for energy should no longer be met, or only in exceptional political situations, by building more power plants that use fossil fuels, as these pollute the environment and contribute to global warming. Therefore, renewable energy is preferred instead – but these are distributed, volatile resources that must be managed within a smart grid infrastructure to ensure a steady supply of energy at all times.
Smart grids allow real-time data from line sensors, loads and generators to be collected and transmitted to a central control point that can perform analysis and control functions. This enables power load balancing, outage restoration and distribution management.
Limitations of the traditional network
Unlike renewable energy generators, whose output depends largely on prevailing weather conditions, conventional fossil fuel power plants provide predictably steady energy. However, they come up against the barrier of environmental sustainability and should accordingly be taken off the grid wherever and whenever possible.
In the meantime, demand for electricity is steadily increasing as, for example, we increasingly take our personal and work lives online and use more and more electric vehicles. So without technological advances, we would be faced with a shrinking stock of fossil fuel power plants that would have to serve an incessant increase in demand for electricity.
This strain would have led to an increasing frequency of power anomalies and blackouts on aging grids that have limited ability to detect and respond to faults in real time.
Fortunately, there are now new technologies being deployed to address these issues. These technologies, and in particular the way they work together, can be grouped under the umbrella term “smart grid”.
[infobox headline=”The morst important facts in brief”]
- Power grids are becoming more complex as demands for reliability, efficiency, safety, and environmental and energy sustainability continue to rise
- The technology behind smart grids makes the power distribution system more efficient, reliable and sustainable
- Smart grids enable power load balancing, outage restoration, and optimize distribution management
- With smart grids and renewable energy sources, electricity consumers can move from pure consumption to “prosumerism”
- Smart meters: By 2032, all electricity consumers in Germany must have at least one digital meter without a gateway
- Semiconductors: The use of modern power electronics could save more than a quarter of electrical energy
- Smart grids could also solve the problem of charging stations for electric vehicles in the future
- Once the technology is fully installed, including in the field, the potential for energy costs to drop significantly and for real-time data control and large-scale charging to become easier increases
- Hive Power offers innovative solutions for smart grids
[/infobox]
Smart grid technologies and interactions
Renewable energies have the advantage that they are clean and cost less and less. However, in addition to the aforementioned disadvantage of volatility, there is also the challenge that plants such as wind farms tend to be widely dispersed rather than centralized.
For this newer grid model, with its multiple distributed energy sources, to function reliably and efficiently, it must be monitored and controlled. It can be thought of as a typical IoT application. Data can be collected in real time from line sensors, loads and generators and relayed to a central control point that can perform analysis and control functions. This enables balancing of power loads, troubleshooting of outages, and management of distribution.
It also facilitates peak shaving, where grid operators can draw on energy supplies from users’ on-site renewable energy systems or even batteries to supplement their own capacity during periods of high demand.
The grid is developing self-healing properties as control systems can detect simple problems and make repairs without intervention. More serious damage to the infrastructure can be reported to technicians in the control center so that timely repairs can be made. To further improve reliability and uptime, the grid can become adaptive, meaning that power is rerouted to bypass problem areas. In this way, the area affected by power outages is limited.
Germany’s progress in renewable energies
In 2020, Germany exceeded all forecasts and achieved 45% renewable energy based on total gross energy consumption. 33% of this came from solar and wind power, the most volatile energy sources. Globally, a 30% share of renewables has been achieved, and grids today, thanks to a combination of robust infrastructure and smart grid technology, are not only cleaner, but also more reliable and resilient.
Digitization allows us to transform the complexity of the modern grid from a weakness to a strength.
This is necessary for the operation of the modern grid, where distributed energy resources (DERs) are on the rise – from small solar and wind farms to electric vehicles (EVs), homes with solar panels, and commercial microgrids. Literally hundreds of millions of new supply points are added to the grid every year. The number of electric vehicles is also growing exponentially, with 26 million vehicles expected to be sold in the U.S. alone by 2030, up from 5.6 million this year.
Possible savings through smart grids
Digitization – sensors, artificial intelligence, and automation – harnesses the combined power of all these DERs and shifts electricity demand in buildings and e-vehicles to times when solar and wind power are available. In this way, cities can use more renewable energy and less fossil fuel backup power. This demand flexibility also helps to mitigate peak demand. In the EU alone, the flexibility of smart grids could save billions annually from now until 2030, as infrastructure expansion can be adjusted to the necessary level.
And the cost savings go even further, extending to ordinary electricity consumers. With smart grids and renewables, electricity consumers can move from pure consumption to “prosumerism,” meaning they can generate and consume electricity themselves and even sell the rest back to the grid.
Imagine 26 million electric car drivers who can charge their vehicles on the grid. At 40 kWh per e-vehicle, they could sell enough clean electricity back to the grid to power 100,000 U.S. homes for an entire year. Prosumerism could make clean electricity affordable for many more people.
The International Renewable Energy Agency also recommends smart grids for developing countries to meet rising renewable electricity demand while creating new opportunities for economic growth.
Universal access to clean electricity is central to a successful energy transition. Specific care must be taken to ensure that people can use safe, smart, sustainable electricity wherever they cook, heat, cool, drive, etc.
All the answers to the question of how we can achieve net zero emissions globally by 2050 may not yet be answered. The potential of green hydrogen and other innovations is still being explored to curb the emissions in aviation, shipping and heavy industry.
But the technology we need to meet the U.N. Environment Program’s goal of halving global emissions by 2030 already exists. In fact, clean electrification of buildings, industry and transport could eliminate three-quarters of global emissions.
Application scenarios for smart grids
While the conventional power grid distributes the electricity generated centrally by large power plants to consumers, smart grids also bring together all the data streams of the energy supply. For example, the highly fluctuating feed-ins from solar and wind power plants can be efficiently balanced and specifically controlled in the existing power grids. The amounts of energy generated and consumed must be continuously measured and analyzed by IoT-enabled sensors and devices.
Smart meters
On the consumer side, this is addressed with smart meters. They also control the feed-in of solar power when consumers with a solar system on the roof also become electricity producers (prosumers). Installation of the necessary smart metering systems (iMSys) is not mandatory until annual electricity consumption exceeds 6,000 kWh – or when consumers feed electricity into the grid themselves. In this case, a smart meter gateway (SMGW) with an integrated security module receives the metering data and processes it for external market participants, internal controllable energy consumers and energy generators (smart household appliances, photovoltaic systems). By 2032, all electricity consumers in Germany must have at least one digital meter without a gateway.
Semiconductors for the energy transition
Measuring, controlling, transforming and communicating – power electronics are of particular importance in the energy transition. While photovoltaic systems or batteries, for example, supply direct current, wind turbines deliver alternating current at a frequency that cannot be used directly. At the same time, electricity consumers have individual needs in terms of current and voltage. The energy-saving potential is immense, because statistically speaking, electricity already passes through at least one converter on its way from the generator to the consumer. According to a study by the European Center for Power Electronics (ECPE), more than a quarter of electrical energy could be saved by using modern power electronics.
And in some areas, silicon is no longer the first choice. Wide bandgap semiconductors, such as the increasingly used silicon carbide (SiC) and gallium nitride (GaN), benefit from higher switching power while maintaining low losses. However, according to analysts at Yole Développement, the technology is still at an early stage of development. They expect SiC devices to generate $6.3 billion in sales in 2027. In the meantime, silicon devices continue to surprise with significant performance gains and will continue to be a source of revenue for the industry in the coming decades. In general, thermal management, robustness, reliability and ultimately packaging continue to be key issues in semiconductors.
Embedded systems
Semiconductors are also the building blocks of embedded systems in a digital, networked and automated energy world. For example, they provide data on the state of the grid, the temperature, the current flow and the angle of the cables. The data is processed in the cloud or directly on site (edge) with AI algorithms. Embedded systems are also transforming traditional building automation into a form of prediction-based management that offers significant potential for energy savings. And in the future, buildings with smart meters (iMSys) connected to a smart grid will not only be able to optimize their own consumption, but also take on the role of electricity producer themselves by feeding surplus energy into the grid.
Interview with Hive Power –Innovative solutions for smart grids
Founded in Switzerland in 2017, Hive Power is a leading provider of innovative smart grid solutions. Hive Power offers a SaaS platform that optimizes existing electrical distribution networks, both from a technical and economic point of view.
Hive Power’s team consists of researchers and scientists with deep knowledge in smart grids, data science and optimization with many years of experience in research and pilot projects on distributed energy management. We spoke with Mr. Gianluca Corbellini, CEO of Hive Power and appreciate the informative answers.
5 Questions for Mr. Ginaluca Corbellini from Hive Power
Q: What has your experience been like tackling the traditional grid with new ideas?
A: It’s been an impactful journey. When we set out in 2017, we had a clear objective to optimize flexibility management for distribution grids and energy suppliers. And we have proven our viability and market fit with our applications for Flexibility Orchestration used in operation by our customers who are innovating from the traditional grid into the smart grid.
Through the help of key mobility industry players, we have tested smart-grid applicable solutions like Vehicle-to-Grid and EV smart charging and produced the FLEXO Smart EV Charging solution that serves automotive companies and EV fleet managers.
Q: What’s your most interesting smart grid application project so far?
A: It’s hard to choose because we worked on amazing smart grids, mobility research, and pilot projects around Europe. One that stands out is called DrainSpotter. It’s unique because we’re developing a solution that faces the consumers and the Distribution System Operator – in this case, AEM.
DrainSpotter is an intuitive mobile application that consumers can use to monitor their electricity usage over time, receive informative summaries of their consumer behaviour, and be automatically notified about anomalies detected by machine learning algorithms.
Through this app, AEM’s residential users eliminate excessive standby power – over 200 W. If they do this consecutively for two weeks, AEM will deliver 10% less energy in total, and 5% of customers would reduce their total energy consumption by at least 20%, and 4.2% of customers would save at least €513 off their total energy bill over 1.5 years.
Q: Looking at the entire smart grid market in Europe, how is Germany performing relatively?
A: As you’ve pointed out earlier, Germany excels in their renewable energy journey. In the first half of this year, 49% of the power used in Germany was generated from renewable sources – that translates into a growth in smart grid adoption. Judging from the SINTEG project, the German government seems committed to increasing smart grid technology. There’s a reliable forecast that Germany’s smart grid investment will increase to $23.6 billion between 2016 and 2026.
There’s a lot of potential in this market, especially in the applications of Electric vehicles, as the boom of EVs is coming alongside smart grids. EV charging in Germany will need to be smarter and more cost-effective as they can interact with the grid and provide Vehicle-to-Grid services using enabling platforms like our FLEXO Smart EV Charging.
Q: How important are smart meters in this innovative smart grid journey?
A: Smart meters make smart grids possible! A smart grid uses advanced metering infrastructure (AMI) (which consists of smart meters, sensors, communications protocols and data management systems) to monitor and control energy demand, distribution, and generation in near real-time.
We need more smart meters to enable our innovative grid systems to make accurate decisions and predictions from the data generated at these smart meter points. For example, the AI algorithms we create in Hive Power are made possible by the enormous amount of data collected from smart meters.
Q: Lastly, What would you say are the most important benefits of smart grids?
A: Sustainability, cost-saving, and energy decentralization!
Having sustainable earth is the grand reason why we are promoting renewable energy sources; we want to reduce greenhouse gas emissions. Smart grids make it possible to effectively manage and optimize the mix of these variable sources of energy without interrupting the energy supply. Consequently, smart grids save energy consumers and producers a lot of costs through proper grid balancing, voltage and frequency anomaly detection, and demand response.
Lastly, smart grids make it possible for us to have integrated microgrids. So homes or communities can produce renewable energy, manage their energy, and sell and buy from the main grid as needed. Sounds impressive, right? We are active in this field and making outstanding contributions to projects around Europe with our FLEXO Community Manager.
Thank you Mr. Corbellini for the exciting interview – we at magility look forward to following the developments of Hive Power further.
Magility’s vision of the future
Smart grid technology is booming, and the federal government is offering incentives for implementation. In addition, smart meter installations are expected to increase. As the cumulative market capitalization will increase exponentially in the coming years, this could be the beginning of a new era.
The smart grids of the future could also solve the problem of charging stations for electric vehicles. But they are not only valuable for closing the gap between supply and demand for intermittent renewable energy sources.
With sufficiently intelligent power grids, power spikes and the frequency of power outages can be prevented. Once this technology is fully installed, including in the field, it will also be able to significantly reduce energy costs and facilitate real-time data control and large-scale charging.
At Magility, we are watching these exciting developments and will keep you updated.
Feel free to follow us on LinkedIn to never miss another article.