Modeling of energy networks - supply quality through storage arrangement

The increasing distributed energy quota in the production mix increases volatility in networks putting supply quality and end user devices at risk, increasing outages and driving utility cost. Deciding on the best placement of storage units in the network is computationally hard. 

Scheduling and duty schedule optimization

Meeting the employees’ personal preferences, while fulfilling the employer’s timing and qualification requirements, legal and labor law constraints etc. and generating fair and robust shift plans is computationally difficult – especially for larger groups of employees.

Detection of anomalies and fraud in financial transactions

Fraudulent financial transactions carry the risk of high losses. Financial institutions require automated detection of anomalous transactions with high precision and low false negative rates to reduce expensive interventions. Performing this task reliably and fast on unlabeled data is challenging.

Modeling of energy networks - cost-optimized planning

The increasing decentralized energy generation and demand requires fine-grained grid operation and planning at near-optimal cost. Additionally, increasing regenerative energy sources lead to volatile supply, which needs to be balanced by committing traditional power generators. Grid planning including this unit commitment is computationally hard.

Security building blocks for digital ecosystems

Vandalism and defects in water pipes cause immense cost due to water damage. Slowly increasing damage is often detected very late (not only in times of low utilization), therefore resulting in high repair cost and long downtimes. 

Water anomaly detection in public buildings

Vandalism and defects in water pipes cause immense costs due to water damage. Slowly increasing damages are often detected very late (not only in times of low utilization), which leads to high repair costs and long downtimes. 

Municipal registers AI

Federal law requires administration to offer its services online to citizens by 2022. Citizens should not be required to enter data already known to some authority. For that, data must be shared across registers and individuals should be identified across them even though often no unique feature exists yet.

Dynamic Vehicle Routing Problem

The Dynamic Vehicle Routing Problem routes a fleet of cars with certain properties such as capacities in (complex) graphs like in warehouses or in cities. The task of the fleet is the transportation of dynamically ascending traffic.

Route planning

Finding an optimal route through a graph visiting each edge. Companies with large infrastructures (like for instance rail networks) need an inspection plan being monitored by an autonomous drones or other vehicles. 

Prediction of material and process properties

The costs associated with design and discovery of materials and chemicals with custom-tailored properties and synthesis of candidate materials can be reduced using simulations. Simulating properties of materials and molecules from first principles is numerically challenging on classical computers (“exponential wall”).

IP Traffic Engineering

Optical Transport Layer optimization, IP traffic engineering and quantum communication network planning are disciplines to optimize the main assets of a telecommunications provider. Choosing an optimum deployment footprint helps to save costs while being able to deliver the best customer experience. 

Data Driven CRM

Understanding customers from their digital footprint in the Telecommunication networks. 

Industrial production lines

In almost every manufacturing or production setting, job shop scheduling problems arise. They themselves are hard to solve. Often, this is accompanied by other optimization problems that interfere with the scheduling, such as the nesting of parts in the example of a sheet metal production. 

Anomaly detection in network communication

Complex attacks on the IT infrastructure compromise network security. To detect these sophisticated threats anomaly detection and will be deployed, to analyze the network flow in near real-time high precision. Machine learning will be used to amplify  the visibility of possible security risks.

Capacity and circulation optimization

Based on a given railway track allocation, transportation companies need to schedule their existing vehicles to optimize the capacity utilization and ensure a trouble-free operation. Especially, if deviations from the original planning occur, a quick response is required to close the supply gaps and maintain all connections. 

Multi-aircraft routing

In coordination with air traffic control organizations, trajectories are computed for aircraft (i) in the uninterrupted case and for the interference cases (ii) thunderstorm, (iii) closed runway, and (iv) closed airspace. From these calculations, a forecast of flight paths in the hourly range is derived. The transfer of path-finding algorithms to quantum computing seems promising here.

Preventive maintenance of trains

In railroad operations, state-of-the-art knowledge related to quantum-based machine learning is needed in the context of preventive maintenance plans. The event to be predicted is basically the failure of a vital component. In the case mentioned, it is power semiconductors. With conventional neural networks, good results are already obtained, measured by the misclassification probabilities. The goal of the new use case is to further reduce the misclassification probabilities with quantum assisted machine learning methods (QNN, etc.).

QKI for assisted COVID-19 reporting and decision support.

The basic idea is to use quantum computing to analyze radiological reporting data images of the lung and surrounding organs in relation to the diagnosis of Covid-19.

Quantum Rail Recovery

Public transportation networks around the world are extremely vulnerable to planned and unplanned disruptions. A minor incident or public protest on or around a passenger rail network can result in system-wide delays and outages. The delay of a single train leads to cascading effects on many other participants in the network and to large operational losses. Mathematical programming approaches to network recovery are referred to as the train driver or aircraft recovery problem.

Quantum Organic Chemistry Pipelines

The production of drugs, such as theophylline for the therapeutic treatment of lung diseases is based on the energy-efficient production of precursors (e.g., methylamine) in mostly catalytic processes. Accurate prediction of molecular properties and derived reaction rates are important fundamentals for improving energy efficiency and thus reducing costs in precursor production.

Timetable optimization for schools

The individual entities (subjects, students, teachers, classes, courses, grades, rooms as well as other resources) offer very individual conditions in schools (e.g. sports preferably in the afternoon in double lessons, ethics at the same time as catholic religion etc.) and besides the pure room and lesson planning also the allocation between students and classes/courses for optimal learning groups could play a role. 

Nesting and revenue management in flexible sheet metal production

Since flexible sheet metal manufacturing is to a large extent a make-to-order business, principles of revenue management (known e.g. from airlines) can be applied. In revenue management, the best way must be found to keep capacity free from highly profitable orders and still use the capacity to its full potential, since it is not storable (e.g. seat in the airplane, machine hour in production). The biggest difference here is that the variable costs do not approach zero, so that it is not the revenue but the contribution margin that must be maximized. In addition, there are two capacity constraints in sheet metal production: Firstly, by the available machine hours, and secondly, by the sheet metal dimensions and the nesting density created by the layout. 

Warehouse optimization

In production or even in the mail order business, goods have to be retrieved from or deposited in the warehouse. The planning of such warehouses is complex and therefore time-consuming, which leads to the fact that a rearrangement in the warehouse to adapt the travel times to the current production or order situation is not carried out. Machine learning can be used to detect changes in current requirements and use them to make forecasts. As a reaction to this, a foresighted re-sorting of the warehouse can be carried out. However, this is only possible when working with flexible transport systems that are controlled centrally. 

QKD Network Optimization

Quantum communication networks are used to defend against the threat of quantum computers, which use Shor's algorithm to attack the confidentiality of our communication networks. QKD (quantum key distribution) systems are one possible defense strategy. But how do we plan for quantum networks on a large scale? How do we minimize the cost of a possible rollout? The goal of securing communications networks throughout Germany requires immense investment. 

Flood protection

Floods are a constant source of concern and are often associated with climate change. The nature of precipitation has changed considerably as a result of climate change. Depending on the nature of the soil, some of the water seeps away and emerges in natural springs (water cycle). Water that does not percolate runs off superficially into bodies of water or into local sewage systems. There is increased overloading of sewage systems and water bodies, up to and including flood events. The necessary investments in flood protection and in wastewater systems are enormous for municipalities and water boards. Flooding due to sudden heavy rainfall events is difficult to predict as things stand, and this is particularly true away from major rivers.

Personnel management in hospitals in response to crises

By using a "QAGA (Quantum-Assisted Genetic Algorithms)" approach as the basis for a QKI application, hospitals should be able to react much more easily to massively changing circumstances in their planning. This involves reconciling shifts in staffing needs by hospitals (overall need, but also location of need) with a more or less abrupt drop in available staffing capacity (driven by waves of illness, lock-down, etc.).

Circuit planning in information processing

Effective models for the diffusion of electrons in relevant materials are used to plan circuits for processors and storage media. As circuits become smaller and approach the limits of quantum mechanics, the parameters for the effective models must be determined from quantum mechanical calculations.

Predictive analytics in population forecasting.

The provision of AI-based population development forecasts, as well as AI-based infrastructure planning, contribute significantly to efficient urban planning. In this way, better decisions can be made as to whether, for example, new development areas should be opened up (a first AI-based model for this is available) or new schools should be built. AI-based planning assistance in financial administration makes it possible to allocate future expenditures more efficiently. Similarly, AI in administrative complaint management enables more precise predictions of where (e.g., area, office, citizen service) which complaints are received and which countermeasures are effective.