• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.14 no.8
• /
• pp.626-633
• /
• 2002

The electric power load during the peak time in summer is strongly affected by cooling load, which decreases the preparation ratio of electricity and brings about the failure in the supply of electricity in the electric power system. The ice-storage system and heat pump system etc. are used to settle this problem. In this study, the method of estimating temperature and humidity to forecast the cooling load of ice storage system is suggested. And also the method of forecasting the cooling load using neural network is suggested. For the simulation, the cooling load is calculated using actual temperature and humidity, The forecast of the temperature, humidity and cooling load are simulated. As a result of the simulation, the forecasted data is approached to the actual data.

• International Journal of Air-Conditioning and Refrigeration
• /
• v.11 no.4
• /
• pp.170-177
• /
• 2003

The electric power load during the summer peak time is strongly affected by cooling load, which decreases the preparation ratio of electricity and brings about the failure in the supply of electricity in the electric power system. The ice storage system and heat pump system etc. are used to settle this problem. In this study, the method of estimating temperature and humidity to forecast the cooling load of ice storage system is suggested. The method of forecasting the cooling load using neural network is also suggested. The daily cooling load is mainly dependent on actual temperature and humidity of the day. The simulation is started with forecasting the temperature and humidity of the following day from the past data. The cooling load is then simulated by using the forecasted temperature and humidity data obtained from the simulation. It was observed that the forecasted data were closely approached to the actual data.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.53 no.3
• /
• pp.188-195
• /
• 2004

This paper presents neural load torque observer that is used to deadbeat load torque observer and gain compensation by parameter estimator As a result, the response of the PMSM(permanent magnet synchronous motor) follows that nominal plant. The load torque compensation method is composed of a neural deadbeat observer To reduce the noise effect, the post-filter implemented by MA(moving average) process, is adopted. The parameter compensator with RLSM (recursive least square method) parameter estimator is adopted to increase the performance of the load torque observer and main controller The parameter estimator is combined with a high performance neural load torque observer to resolve the problems. The neural network is trained in on-line phases and it is composed by a feed forward recall and error back-propagation training. During the normal operation, the input-output response is sampled and the weighting value is trained multi-times by error back-propagation method at each sample period to accommodate the possible variations in the parameters or load torque. As a result, the proposed control system has a robust and precise system against the load torque and the Parameter variation. A stability and usefulness are verified by computer simulation and experiment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.4
• /
• pp.651-669
• /
• 2013

In this paper, we study a novel routing algorithm based on load balancing for multi-channel wireless mesh networks. In order to increase the network capacity and reduce the interference of transmission streams and the communication delay, on the basis of weighted cumulative expected transmission time (WCETT) routing metric this paper proposes an improved routing metric based on load balancing and channel interference (LBI_WCETT), which considers the channel interference, channel diversity, link load and the latency brought by channel switching. Meanwhile, in order to utilize the multi-channel strategy efficiently in wireless mesh networks, a new channel allocation algorithm is proposed. This channel allocation algorithm utilizes the conflict graph model and considers the initial link load estimation and the potential interference of the link to assign a channel for each link in the wireless mesh network. It also utilizes the channel utilization percentage of the virtual link in its interference range as the channel selection standard. Simulation results show that the LBI_WCETT routing metric can help increase the network capacity effectively, reduce the average end to end delay, and improve the network performance.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.6
• /
• pp.109-116
• /
• 2007

The lack of load-balancing functionality in most existing ad hoc routing protocols often causes congestion resulting in bad performance and short lifetime of participating nodes. We present an auxiliary scheme for reactive routing protocols to discover an unloaded route, thereby decreasing possibility of congestion. The scheme allows an intermediate node to determine whether to be a relaying node for a newly constructed route autonomously based on the occupancy of its queue. Thus the scheme does not require network-wide load information. Simulation results show that the proposed scheme distributes traffic load well.

• ETRI Journal
• /
• v.38 no.5
• /
• pp.962-971
• /
• 2016

A wireless power transfer (WPT) system is generally designed with the optimum source and load impedance in order to achieve the maximum power transfer efficiency (PTE) at a specific coupling coefficient. Empirically or intuitively, however, it is well known that a high PTE can be attained by adjusting either the source or load impedance. In this paper, we estimate the maximum achievable PTE of WPT systems with the given load impedance, and propose the condition of source impedance for the maximum PTE. This condition can be reciprocally applied to the load impedance of a WPT system with the given source impedance. First, we review the transducer power gain of a two-port network as the PTE of the WPT system. Next, we derive two candidate conditions, the critical coupling and the optimum conditions, from the transducer power gain. Finally, we compare the two conditions carefully, and the results therefore indicate that the optimum condition is more suitable for a highly efficient WPT system with a given load impedance.

• Journal of Korea Society of Industrial Information Systems
• /
• v.15 no.5
• /
• pp.97-104
• /
• 2010

In this paper, mesh network structure is applied to solve the load balancing problems in the Grid database. Data of the Grid database is replicated to several node for enhanced performance. Therefore, load balancing for user's query is selected node that evaluated workload in it. Existing researches are using passive load balancing method that selected another node after then node overflowed workload. It is inefficient to be applied to Gird database that has a number of node and user's queries almost changes dynamically. The proposed method connected each node which includes the same data through mesh network structure. When user's query occurs, it select node that has the lowest workload. The performance evaluation shows that proposed method performs better than the existing methods.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.1
• /
• pp.151-160
• /
• 2024

Artificial Neural Networks that enabled Artificial Intelligence are being used in many fields. However, the application to mechanical structures has several problems and research is incomplete. One of the problems is that it is difficult to secure a large amount of data necessary for learning Artificial Neural Networks. In particular, it is important to detect and recognize external forces and forces for safety working and accident prevention of mechanical structures. This study examined the possibility by applying the Current Neural Network of Artificial Neural Networks to detect and recognize the load on the machine. Tens of thousands of data are required for general learning of Recurrent Neural Networks, and to secure large amounts of data, this paper derives load data from ANSYS structural analysis results and applies a stacked auto-encoder technique to secure the amount of data that can be learned. The usefulness of Stacked Auto-Encoder data was examined by comparing Stacked Auto-Encoder data and ANSYS data. In addition, in order to improve the accuracy of detection and recognition of load data with a Recurrent Neural Network, the optimal conditions are proposed by investigating the effects of related functions.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.41 no.1
• /
• pp.1-8
• /
• 1992

Hopfield neural network has been applied to the problem of economic load dispatch(ELD) of electric power. The optimum values of neuron potentials are represented in terms of large numbers. The differential synchronous transition mode is used in this simulation. Through case studies, we have shown the possibility of the application of neural network to ELD. In case of including the transmission losses, the proposed method has an advantage that the problem can be solved simply with one neural network, without calculating incremental fuel costs and incremental losses required by traditional method.

• The Journal of Society for e-Business Studies
• /
• v.9 no.3
• /
• pp.277-288
• /
• 2004

The purpose of multimedia contents transmission is to resolve the large size and nonformal issues. Various multicasting technologies have been researched to support these issues. This paper suggests a technique to build multicast routing for safe and reliable transmission of multimedia contents. Network server nodes have their own weight with respect to communication loads. The weight is computed by a server's communication load with others. This suggests low delay routing with two or more edge server of content delivery network. We will show the weighted inter-server routing technique and analyze the network performance improvement caused by lower network traffic and delay.