The mission-critical operations of smart distribution grids necessitate highly reliable and low-latency communication to ensure uninterrupted electricity distribution with high security of supply. The 5G networks (and...
详细信息
ISBN:
(纸本)9798350318562;9798350318555
The mission-critical operations of smart distribution grids necessitate highly reliable and low-latency communication to ensure uninterrupted electricity distribution with high security of supply. The 5G networks (and beyond), will provide a diverse range of services for various customers, network operators, and verticals. This is enabled by the flexibility provided by increased softwarization and virtualization of the networks, including network slicing. In an intent-based network, the tenants can express the desired outcome of a communication service using intents at an abstract level. Due to the highly dynamic nature of communication service requests, it is very challenging for the network provider to make the trade-off between accepting or rejecting a request while allocating resources to meet the tenants' expectations as defined by the service level objectives. In this paper, we implemented a discreteevent simulation, including a two-tier admission control mechanism for service requests. The simulation results compare four admission control policies upon the arrival of service requests into the network-sliced environment and provide interesting parameters, such as the probability of violating a service level objective, which implies a breach of the service level agreement. Our findings in the paper highlight the importance of priority enforcement, two-tier admission control, and resource reserving strategies to meet the desired objectives of mission-critical traffic in smart distribution grid protection.
With the advent of big data in electricity power, concerns about privacy and security have led most power stations to avoid sharing their electricity data, resulting in 'data islands.' Federated learning emerg...
详细信息
In 2021, the country proposed the strategic goal of "carbon peaking and carbon neutrality". In order to actively respond to the national strategy and complete the implementation of the strategy, it was propo...
详细信息
-With the development of the smart grid, electricity consumption forecasting has become increasingly important in power systems. Accurate forecasting not only helps power companies optimize their operation strategies ...
详细信息
In many computing applications, grid-based algorithms areessential, particularly in the gaming industry where performance, shortest path and efficiency are crucial. In order to find the best algorithm for gaming sett...
详细信息
Theelectricity system with penetration of a massive number of renewable generation sources needs to consider various demands, such as power generation efficiency, the service life of energy storage devices, and its i...
详细信息
The phenomenon of reflection superposition manifests itself as complex and prevalent in the real world, leading to theemergence of various simplified linear and non-linear formulas and related models. This study poin...
详细信息
Tactile sensors with impact localization are becoming an essential part in automotive, aerospace, and civil engineering for damage assessment, safety assurance and structural monitoring. Inkjet printing is on rise for...
详细信息
ISBN:
(纸本)9798350387186;9798350387179
Tactile sensors with impact localization are becoming an essential part in automotive, aerospace, and civil engineering for damage assessment, safety assurance and structural monitoring. Inkjet printing is on rise for its eco-friendliness, cost-efficiency, low power consumption and quick design iteration ability. However, its minimal fabrication process results in operational challenges. These challenges can be mitigated by integrating artificial intelligence with inkjet printed sensors to enhance their performance. Among all artificial intelligences, echo state networks are gaining recognition for their low computational demands and hardware compatibility. This study developed an inkjet-printed tactilegrid sensor with an echo state network for impact localization. The sensitivity of sensor was assessed through a pencil drop experiment, with data transformation across time and magnitude domains to improve network adaptability. Hyperparameters of the model were fine-tuned through sequential search. Developed echo state network with grid tactile sensor demonstrated high accuracy, pinpointing the impact location of pencil drops with an impressive precision rate of 94.89%.
We analyze a networking system powered by solar panels, where the harvested energy is stored in a battery that can also be sold when fully charged. Then the networking operator faces dual objectives: maintaining the f...
详细信息
ISBN:
(纸本)9798350387452;9798350387445
We analyze a networking system powered by solar panels, where the harvested energy is stored in a battery that can also be sold when fully charged. Then the networking operator faces dual objectives: maintaining the functionality of its infrastructure and selling (or supplying to other networks) the filled batteries. These two goals are contradictory as selling the battery's energy may result in operational disruptions (e.g., packet delays) during certain periods. To address these challenges, we have developed a Markovian Decision Process (MDP) model that integrates positive rewards for battery release as well as penalties for energy packet loss and battery depletion. From this modeling, we present the optimal policy that balances these conflicting objectives and maximizes an average reward function. We advocate that integrating the particular structure of the MDP will enhanceefficiency and precision of the numerical analysis. We provide numerical comparisons from small-scale to large-scale models and present a detailed analysis of agent behavior under the optimal policy.
computing power network (CPN) is a distributed network system designed to connect and integratecomputing resources globally, enabling efficient sharing and utilization of computing power. In dependent task offloading...
详细信息
ISBN:
(纸本)9798350363999;9798350364002
computing power network (CPN) is a distributed network system designed to connect and integratecomputing resources globally, enabling efficient sharing and utilization of computing power. In dependent task offloading, the dependency relationship between tasks is generally used to determine theexecution order. However, the assignment phase often overlooks the relevance and sharing between tasks, leading to a waste of system resources in CPNs. In the learning process, agents frequently encounter the issue of sparse rewards, which results in slow learning and makes it challenging to develop effective strategies. To address the aforementioned issues, we design a dependent task offloading method based on hypergraph partitioning and an intrinsic curiosity module, i.e., HP-ICM, which offloads tasks with similar resource requirements or dependencies into the same partition and utilizes the ICM to enhance the speed and quality of learning. Simulation results show that HP-ICM can reduce latency by 22.8% and energy consumption by 25.7% compared to the PPO baseline during task offloading.
暂无评论