• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 하계학술대회 논문집 D
• /
• pp.797-799
• /
• 1997

This paper presents an operation and planning model of integrated energy systems which consist of small scale cogeneration systems, thermal accumulator, ice storage and electrical energy storage systems. In the proposed planning model, an optimization of total cost which contains investment, operation, thermal shortage and salvage costs has carried out with the maximum principle based on the lifetime of each system component and unit price per capacity. From this model, optimal investment capacity per annum can be determined during the studied periods using the marginal costs according to the operation characteristics of each system component.

• 한국태양에너지학회:학술대회논문집
• /
• 한국태양에너지학회 2011년도 추계학술발표대회 논문집
• /
• pp.359-363
• /
• 2011

Building-integrated photovoltaics(BIPV)are increasingly incorporate into new domestic and industrial buildings as a proncipal or ancillary source of electrical power, and are on of the fastest growing segments of the photovoltaic industry. This paper presents operational features analysis and PCS(Power conversion System) factors of grid-connected 30kW BIPV on library of Dongshin University. The data consisted of insolation, Temperature, solar-cell performance and inverter performance are collected by IVIsion web monitoring system and analyzed. The analyzed data gave this paper effect elements of optimal operation.

• Smart Structures and Systems
• /
• 제24권6호
• /
• pp.733-744
• /
• 2019

Wind speed forecasting is critical for a variety of engineering tasks, such as wind energy harvesting, scheduling of a wind power system, and dynamic control of structures (e.g., wind turbine, bridge, and building). Wind speed, which has characteristics of random, nonlinear and uncertainty, is difficult to forecast. Nowadays, machine learning approaches (generalized regression neural network (GRNN), back propagation neural network (BPNN), and extreme learning machine (ELM)) are widely used for wind speed forecasting. In this study, two schemes are proposed to improve the forecasting performance of machine learning approaches. One is that optimization algorithms, i.e., cross validation (CV), genetic algorithm (GA), and particle swarm optimization (PSO), are used to automatically find the optimal model parameters. The other is that the combination of different machine learning methods is proposed by finite mixture (FM) method. Specifically, CV-GRNN, GA-BPNN, PSO-ELM belong to optimization algorithm-assisted machine learning approaches, and FM is a hybrid machine learning approach consisting of GRNN, BPNN, and ELM. The effectiveness of these machine learning methods in wind speed forecasting are fully investigated by one-year field monitoring data, and their performance is comprehensively compared.

• International Journal of Computer Science & Network Security
• /
• 제22권7호
• /
• pp.301-307
• /
• 2022

Energy consumption has grown alongside dramatic population increases. Statistics show that buildings in particular utilize a significant amount of energy, worldwide. Because of this, building energy prediction is crucial to best optimize utilities' energy plans and also create a predictive model for consumers. To improve energy prediction performance, this paper proposes a ResNet-LSTM model that combines residual networks (ResNets) and long short-term memory (LSTM) for energy consumption prediction. ResNets are utilized to extract complex and rich features, while LSTM has the ability to learn temporal correlation; the dense layer is used as a regression to forecast energy consumption. To make our model more robust, we employed Huber loss during the optimization process. Huber loss obtains high efficiency by handling minor errors quadratically. It also takes the absolute error for large errors to increase robustness. This makes our model less sensitive to outlier data. Our proposed system was trained on historical data to forecast energy consumption for different time series. To evaluate our proposed model, we compared our model's performance with several popular machine learning and deep learning methods such as linear regression, neural networks, decision tree, and convolutional neural networks, etc. The results show that our proposed model predicted energy consumption most accurately.

• 한국수소및신에너지학회논문집
• /
• 제27권1호
• /
• pp.49-62
• /
• 2016

In this study, a solid oxide fuel cell (SOFC) system model including balance of plant (BOP) for building electric power generation is developed to study the effect of operating conditions on the system efficiency and power output. SOFC system modeled in this study consists of three heat-exchangers, an external reformer, burner, and two blowers. A detailed computational cell model including internal reforming reaction is developed for a planer SOFC stack which is operated at intermediate temperature (IT). The BOP models including an external reformer, heat-exchangers, a burner, blowers, pipes are developed to predict the gas temperature, pressure drops and flow rate at every component in the system. The SOFC stack model and BOP models are integrate to estimate the effect of operating parameters on the performance of the system. In this study, the design of experiment (DOE) is used to compare the effects of fuel flow rate, air flow rate, air temperature, current density, and recycle ratio of anode off gas on the system efficiency and power output.

• 대한기계학회논문집B
• /
• 제33권6호
• /
• pp.396-402
• /
• 2009

Recently many efforts have been carried out on the development of energy-efficient and environment-friendly systems in order to preserve natural environment and to reduce environmental loads in the branch of the urban planning and the building design. In this study, a mathematical method was developed and a numerical analysis was carried out with various parameters to provide substantial data for optimal design and operation of urban energy supply systems. Components of the system and their specifications, such as a co-generation system and other heating and cooling systems, could be obtained through this analysis for various resource and energy requirements in urban area. In this study, the system constituents and operating characteristics, and their economic performances such as the value of objective function, the amount of energy consumption were discussed for various load patterns and power load ratios. Also, it turns out that the optimal energy supply system can save energy by $10{\sim}20%$ in comparison with the conventional energy supply system.

• KIEAE Journal
• /
• 제17권5호
• /
• pp.69-76
• /
• 2017

Purpose: This study aimed at developing an Artificial Neural Network (ANN) model for predicting the amount of cooling energy consumption of the variable refrigerant flow (VRF) cooling system by the different set-points of the control variables, such as supply air temperature of air handling unit (AHU), condenser fluid temperature, condenser fluid pressure, and refrigerant evaporation temperature. Applying the predicted results for the different set-points, the control algorithm, which embedded the ANN model, will determine the most energy efficient control strategy. Method: The ANN model was developed and tested its prediction accuracy by using matrix laboratory (MATLAB) and its neural network toolbox. The field data sets were collected for the model training and performance evaluation. For completing the prediction model, three major steps were conducted - i) initial model development including input variable selection, ii) model optimization, and iii) performance evaluation. Result: Eight meaningful input variables were selected in the initial model development such as outdoor temperature, outdoor humidity, indoor temperature, cooling load of the previous cycle, supply air temperature of AHU, condenser fluid temperature, condenser fluid pressure, and refrigerant evaporation temperature. The initial model was optimized to have 2 hidden layers with 15 hidden neurons each, 0.3 learning rate, and 0.3 momentum. The optimized model proved its prediction accuracy with stable prediction results.

• 설비공학논문집
• /
• 제28권10호
• /
• pp.394-401
• /
• 2016

The configuration of an extruded-type cooling structure was optimized for the light-emitting diode (LED) streetlights that have recently replaced convectional metal halide streetlights for energy saving. Natural convection and radiative heat transfer over the cooling structure were simulated using a numerical model with experimental verification. An improved cooling structure type was suggested to overcome the previous performance degeneration, as confirmed by analyzing the thermal flow around the existing cooling structure. A parameter study of the cooling structure geometries was also conducted and, based on the numerical results, the configuration was optimized to reduce the weight of the cooling structure. Consequently, the mass of the cooling structure was reduced by 60%, while the thermal performance was improved by 10%.

• 한국태양에너지학회 논문집
• /
• 제39권3호
• /
• pp.1-7
• /
• 2019

As part of the government's energy policy, Zero Energy Building certification was launched on January of 2017. However, the three passive-housing rental housing projects are the only ZEB-certified detached housing since the certification's launch. The reason is that, in order for a detached housing to earn ZEB certification, it has to secure self-reliance in energy, and a photovoltaic system is the only viable renewable energy system. Therefore, conducting an analysis to optimize the photovoltaic system in an early design stage is strongly recommended. This study aimed to propose an optimal photovoltaic system design for a detached housing after analyzing through the ECO2 energy simulation of 44 cases, varying in a module type and efficiency, inclination and azimuth. As a result, 15 cases out of 44 cases were analyzed to satisfy ZEB evaluation criteria, and it is thought that these data could contribute greatly to the expansion of ZEB certification dissemination.

• 상하수도학회지
• /
• 제30권3호
• /
• pp.321-325
• /
• 2016

The Pressure Retarded Osmosis (PRO) is the next generation desalination technique and is considered as a eco-friendly energy. This was conducted to evaluate the effect of the temperature and pressure on the PRO performance. The flux of the permeation was measured under different operating conditions and estimated the power density. An improvement of PRO performance is depend on increasing solution temperature and optimum pressure. The effect of increasing feed solution temperature has stronger impact on the PRO performance comparing to the draw solution temperature. The reason of the results was due to the change of osmotic power, viscosity, water permeability and structure parameter(s).