• Journal of KIISE:Information Networking
• /
• v.30 no.4
• /
• pp.535-544
• /
• 2003

Integrated services networks should guarantee end-to-end delay bounds for real-time applications to provide high quality services. A real-time scheduler is installed on all the output ports to provide such guaranteed service. However, scheduling algorithms studied so far have problems with either network utilization or scalability. Here, network utilization indicates how many real-time sessions can be admitted. In this paper, we propose service curve allocation schemes that result in both high network utilization and scalability in a service curve algorithm. In service curve algorithm, an adopted service curve allocation scheme determines both network utilization and scalability. Contrary to the common belief, we have proved that only a part of a service curve is used to compute deadlines, not the entire curve. From this fact, we propose service curve allocation schemes that result in a constant time for computing deadlines. We through a simulation study that our proposed schemes can achieve better network utilizations than Generalized processor Sharing (GPS) algorithms including the multirate algorithm. To our knowledge, the service curve algorithm adopting our schemes can achieve the widest network utilization among existing scheduling algorithms that have the same scalability.

• Journal of Software Assessment and Valuation
• /
• v.17 no.1
• /
• pp.101-113
• /
• 2021

In this paper, we introduce a speaker overlap system and look at the process of converting the existed system on the specific framework of artificial intelligence. Speaker overlap is when two or more speakers speak at the same time during a conversation, and can lead to performance degradation in the fields of speech recognition or speaker recognition, and a lot of research is being conducted because it can prevent performance degradation. Recently, as application of artificial intelligence is increasing, there is a demand for switching between artificial intelligence frameworks. However, when switching frameworks, performance degradation is observed due to the unique characteristics of each framework, making it difficult to switch frameworks. In this paper, the process of converting the speaker overlap detection system based on the Keras framework to the pytorch-based system is explained and considers components. As a result of the framework switching, the pytorch-based system showed better performance than the existing Keras-based speaker overlap detection system, so it can be said that it is valuable as a fundamental study on systematic framework conversion.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.3
• /
• pp.73-82
• /
• 2022

Auto-scaling is one of the most important functions for cloud computing technology. Even if the number of users or service requests is explosively increased or decreased, system resources and service instances can be appropriately expanded or reduced to provide services suitable for the situation and it can improves stability and cost-effectiveness. However, since the policy is performed based on a single metric data at the time of monitoring a specific system resource, there is a problem that the service is already affected or the service instance that is actually needed cannot be managed in detail. To solve this problem, in this paper, we propose a method to predict system resource and service response time using a multivariate time series analysis model and establish an auto-scaling policy based on this. To verify this, implement it as a custom scheduler in the Kubernetes environment and compare it with the Kubernetes default auto-scaling method through experiments. The proposed method utilizes predictive data based on the impact between system resources and response time to preemptively execute auto-scaling for expected situations, thereby securing system stability and providing as much as necessary within the scope of not degrading service quality. It shows results that allow you to manage instances in detail.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.3
• /
• pp.72-83
• /
• 2017

GPUs can provide high throughput with latency hiding by executing many warps in parallel. MSHR(Miss Status Holding Registers) for L1 data cache tracks cache miss requests until required data is serviced from lower level memory. In recent GPUs, excessive requests for cache resources cause underutilization problem of GPU resources due to cache resource reservation fails. In this paper, we propose a new warp scheduling technique to reduce stall cycles under MSHR resource shortage. Cache miss rates for each warp is predicted based on the observation that each warp shows similar cache miss rates for long period. The warps showing low miss rates or computation-intensive warps are given high priority to be issued when MSHR is full status. Our proposal improves GPU performance by utilizing cache resource more efficiently based on cache miss rate prediction and monitoring the MSHR entries. According to our experimental results, reservation fail cycles can be reduced by 25.7% and IPC is increased by 6.2% with the proposed scheduling technique compared to loose round robin scheduler.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.213-226
• /
• 2011

In global supply chain, the scheduling problems of large products such as ships, airplanes, space shuttles, assembled constructions, and/or automobiles are complicated by nature. New scheduling systems are often developed in order to reduce inherent computational complexity. As a result, a problem can be decomposed into small sub-problems, problems that contain independently small scheduling systems integrating into the initial problem. As one of the authors experienced, DAS (Daewoo Shipbuilding Scheduling System) has adopted a two-layered hierarchical architecture. In the hierarchical architecture, individual scheduling systems composed of a high-level dock scheduler, DAS-ERECT and low-level assembly plant schedulers, DAS-PBS, DAS-3DS, DAS-NPS, and DAS-A7 try to search the best schedules under their own constraints. Moreover, the steep growth of communication technology and logistics enables it to introduce distributed multi-nation production plants by which different parts are produced by designated plants. Therefore vertical and lateral coordination among decomposed scheduling systems is necessary. No standard coordination mechanism of multiple scheduling systems exists, even though there are various scheduling systems existing in the area of scheduling research. Previous research regarding the coordination mechanism has mainly focused on external conversation without capacity model. Prior research has heavily focuses on agent-based coordination in the area of agent research. Yet, no scheduling domain has been developed. Previous research regarding the agent-based scheduling has paid its ample attention to internal coordination of scheduling process, a process that has not been efficient. In this study, we suggest a general framework for agent-based coordination of multiple scheduling systems in global supply chain. The purpose of this study was to design a standard coordination mechanism. To do so, we first define an individual scheduling agent responsible for their own plants and a meta-level coordination agent involved with each individual scheduling agent. We then suggest variables and values describing the individual scheduling agent and meta-level coordination agent. These variables and values are represented by Backus-Naur Form. Second, we suggest scheduling agent communication protocols for each scheduling agent topology classified into the system architectures, existence or nonexistence of coordinator, and directions of coordination. If there was a coordinating agent, an individual scheduling agent could communicate with another individual agent indirectly through the coordinator. On the other hand, if there was not any coordinating agent existing, an individual scheduling agent should communicate with another individual agent directly. To apply agent communication language specifically to the scheduling coordination domain, we had to additionally define an inner language, a language that suitably expresses scheduling coordination. A scheduling agent communication language is devised for the communication among agents independent of domain. We adopt three message layers which are ACL layer, scheduling coordination layer, and industry-specific layer. The ACL layer is a domain independent outer language layer. The scheduling coordination layer has terms necessary for scheduling coordination. The industry-specific layer expresses the industry specification. Third, in order to improve the efficiency of communication among scheduling agents and avoid possible infinite loops, we suggest a look-ahead load balancing model which supports to monitor participating agents and to analyze the status of the agents. To build the look-ahead load balancing model, the status of participating agents should be monitored. Most of all, the amount of sharing information should be considered. If complete information is collected, updating and maintenance cost of sharing information will be increasing although the frequency of communication will be decreasing. Therefore the level of detail and updating period of sharing information should be decided contingently. By means of this standard coordination mechanism, we can easily model coordination processes of multiple scheduling systems into supply chain. Finally, we apply this mechanism to shipbuilding domain and develop a prototype system which consists of a dock-scheduling agent, four assembly- plant-scheduling agents, and a meta-level coordination agent. A series of experiments using the real world data are used to empirically examine this mechanism. The results of this study show that the effect of agent-based platform on coordinated scheduling is evident in terms of the number of tardy jobs, tardiness, and makespan.