A5060735549- Supply Chain Resilience and Risk Management
- Blockchain Technology Applications and Security
- Quality and Supply Management
- Privacy-Preserving Technologies in Data
- Age of Information Optimization
- Advanced Control Systems Optimization
- Control Systems and Identification
- Analog and Mixed-Signal Circuit Design
- IoT and Edge/Fog Computing
- Advanced Multi-Objective Optimization Algorithms
- Mobile Crowdsensing and Crowdsourcing
- Sustainable Supply Chain Management
- Supply Chain and Inventory Management
Huawei German Research Center
2022-2024
Huawei Technologies (China)
2019-2020
The University of Western Australia
1971
We formulate computation offloading as a decentralized decision-making problem with autonomous agents. design an interaction mechanism that incentivizes agents to align private and system goals by balancing between competition cooperation. The provably has Nash equilibria optimal resource allocation in the static case. For dynamic environment, we propose novel multi-agent online learning algorithm learns partial, delayed noisy state information, reward signal reduces information need great...
Manufacturing companies typically use sophisticated production planning systems optimizing steps, often delivering near-optimal solutions. As a downside for schedule, have high computational demands resulting in hours of computation. Under norma l circumstances this is not issue if there enough buffer time before implementation the schedule (e.g. at night next day). However, case unexpected disruptions such as delayed part deliveries or defectively manufactured goods, planned may become...
The Intelligent Transportation System (ITS) environment is known to be dynamic and distributed, where participants (vehicle users, operators, etc.) have multiple, changing possibly conflicting objectives. Although Reinforcement Learning (RL) algorithms are commonly applied optimize ITS applications such as resource management offloading, most RL focus on single In many situations, converting a multi-objective problem into single-objective one impossible, intractable or insufficient, making...
If the switching criterion of a time-invariant 2nd-order plant is derived on basis energy balance during complete cycle for step-input disturbances, prediction process may be synthetised without implementing optimum curve.