• 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.

• Earthquakes and Structures
• /
• 제8권5호
• /
• pp.957-976
• /
• 2015

Recently, two energy-based response parameters, i.e., the absolute and the relative elastic input energy equivalent velocity, have been receiving a lot of research attention. Several studies, in fact, have demonstrated the potential of these intensity measures in the prediction of the seismic structural response. Although some ground motion prediction equations have been developed for these parameters, they only provide marginal distributions without information about the joint occurrence of the spectral values at different periods. In order to build new prediction models for the two equivalent velocities, a large set of ground motion records is used to calculate the correlation coefficients between the response spectral values corresponding to different periods and components of the ground motion. Then, functional forms adopted in models from the literature are calibrated to fit the obtained data. A new functional form is proposed to improve the predictions of the considered models from the literature. The components of the ground motion considered in this study are the two horizontal ones only. Potential uses of the proposed equations in addition to the prediction of the correlation coefficients of the equivalent velocity spectral values are shown, such as the prediction of derived intensity measures and the development of conditional mean spectra.

• Earthquakes and Structures
• /
• 제18권1호
• /
• pp.73-82
• /
• 2020

With the coal mining depth increasing, both stress and gas pressure rapidly enhance, causing coal and gas outburst risk to become more complex and severe. The conventional method for prediction of coal and gas outburst adopts one prediction index and corresponding critical value to forecast and cannot reflect all the factors impacting coal and gas outburst, thus it is characteristic of false and missing forecasts and poor accuracy. For the reason, based on analyses of both the prediction indicators and the factors impacting coal and gas outburst at the test site, this work carefully selected 6 prediction indicators such as the index of gas desorption from drill cuttings Δh₂, the amount of drill cuttings S, gas content W, the gas initial diffusion velocity index ΔP, the intensity of electromagnetic radiation E and its number of pulse N, constructed the Bayes discriminant analysis (BDA) index system, studied the BDA-based multi-index comprehensive model for forecast of coal and gas outburst risk, and used the established discriminant model to conduct coal and gas outburst prediction. Results showed that the BDA - based multi-index comprehensive model for prediction of coal and gas outburst has an 100% of prediction accuracy, without wrong and omitted predictions, can also accurately forecast the outburst risk even for the low indicators outburst. The prediction method set up by this study has a broad application prospect in the prediction of coal and gas outburst risk.

• 한국태양에너지학회:학술대회논문집
• /
• 한국태양에너지학회 2008년도 추계학술발표대회 논문집
• /
• pp.300-305
• /
• 2008

Using WindPRO that was software for windfarm design developed by EMD from Denmark, wind resources for the western Jeju island were analyzed, and the performance of WindPRO prediction was evaluated in detail. The Hansu site and the Yongdang site that were located in coastal region were selected, and wind data for one year at the two sites were analyzed using WindPRO. As a result, the relative error of the Prediction for annual energy Production and capacity factor was about ${\pm}20%$. For evaluating wind energy more accurately, it is necessary to obtain lots of wind data and real electric power production data from real windfarm.

• International Journal of Automotive Technology
• /
• 제7권6호
• /
• pp.741-747
• /
• 2006

It has been almost impossible to predict the fatigue life in the field of rubber materials by numerical methods. One of the reasons is that there are no obvious fracture criteria and excessively various ways of mixing processes. Tearing energy is considered as a fracture criterion which can be applied to rubber compounds regardless of different types of fillers, relative to other fracture factors. Fatigue life of rubber materials can be approximately predicted based on the assumption that the latent defect caused by contaminants or voids in the matrix, imperfectly dispersed compounding ingredients, mold lubricants and surface flaws always exists. Numerical expression for the prediction of fatigue life was derived from the rate of rough cut growth region and the formulated tearing energy equation. Endurance test data for dumbbell specimens were compared with the predicted fatigue life for verification. Also, fatigue life of industrial rubber components was predicted.

• KEPCO Journal on Electric Power and Energy
• /
• 제5권3호
• /
• pp.223-228
• /
• 2019

In order to integrate large amounts of variable generation resources such as wind and solar reliably into power grids, accurate renewable energy forecasting is necessary. Since renewable energy generation output is heavily influenced by environmental variables, accurate forecasting of power generation requires meteorological data at the point where the plant is located. Therefore, a spatial approach is required to predict the meteorological variables at the interesting points. In this paper, we propose the meteorological variable prediction model for enhancing renewable generation output forecasting model. The proposed model is implemented by three geostatistical techniques: Ordinary kriging, Universal kriging and Co-kriging.

• Asian-Australasian Journal of Animal Sciences
• /
• 제25권10호
• /
• pp.1430-1438
• /
• 2012

The present experiment was conducted to determine the digestible energy (DE), metabolizable energy (ME) content, and the apparent total tract digestibility (ATTD) of energy in growing pigs fed diets containing one of ten cottonseed meals (CSM) collected from different provinces of China and to develop in vitro prediction equations for DE and ME content from chemical composition of the CSM samples. Twelve growing barrows with an initial body weight of $35.2{\pm}1.7$ kg were allotted to two $6{\times}6$ Latin square designs, with six barrows and six periods and six diets for each. A corn-dehulled soybean meal diet was used as the basal diet, and the other ten diets were formulated with corn, dehulled soybean meal and 19.20% CSM. The DE, ME and ATTD of gross energy among different CSM sources varied largely and ranged from 1,856 to 2,730 kcal/kg dry matter (DM), 1,778 to 2,534 kcal/kg DM, and 42.08 to 60.47%, respectively. Several chemical parameters were identified to predict the DE and ME values of CSM, and the accuracy of prediction models were also tested. The best fit equations were: DE, kcal/kg DM = 670.14+31.12 CP+659.15 EE with $R^2$ = 0.82, RSD = 172.02, p<0.05; and ME, kcal/kg DM = 843.98+25.03 CP+673.97 EE with $R^2$ = 0.84, RSD = 144.79, p<0.05. These results indicate that DE, ME values and ATTD of gross energy varied substantially among different CSM sources, and that some prediction equations can be applied to predict DE and ME in CSM with an acceptable accuracy.

• Nuclear Engineering and Technology
• /
• 제55권1호
• /
• pp.339-352
• /
• 2023

Prediction of the time-related traits of pebble flow inside pebble-bed HTGRs is of great significance for reactor operation and design. In this work, an image-driven approach with the aid of a convolutional neural network (CNN) is proposed to predict the remaining time of initially loaded pebbles and the time interval of paired flow images of the pebble bed. Two types of strategies are put forward: one is adding FC layers to the classic classification CNN models and using regression training, and the other is CNN-based deep expectation (DEX) by regarding the time prediction as a deep classification task followed by softmax expected value refinements. The current dataset is obtained from the discrete element method (DEM) simulations. Results show that the CNN-aided models generally make satisfactory predictions on the remaining time with the determination coefficient larger than 0.99. Among these models, the VGG19+DEX performs the best and its CumScore (proportion of test set with prediction error within 0.5s) can reach 0.939. Besides, the remaining time of additional test sets and new cases can also be well predicted, indicating good generalization ability of the model. In the task of predicting the time interval of image pairs, the VGG19+DEX model has also generated satisfactory results. Particularly, the trained model, with promising generalization ability, has demonstrated great potential in accurately and instantaneously predicting the traits of interest, without the need for additional computational intensive DEM simulations. Nevertheless, the issues of data diversity and model optimization need to be improved to achieve the full potential of the CNN-aided prediction tool.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 춘계학술대회
• /
• pp.858-861
• /
• 2012

무선 센서 네트워크를 이용한 응용들 중 특히 환경 모니터링을 위해 대량으로 배치된 센서 노드들은 배터리 교체가 어렵고 교체시에 비용이 많이 드는 단점이 있다. 이를 보완하기 위해서는 무선 센서 네트워크 주위에 존재하는 신재생 에너지를 이용할 필요가 있다. 신재생 에너지들 중 태양 에너지는 매일 사용할 수 있고 에너지의 밀도가 다른 에너지원들 보다 높아 많이 이용되고 있다. 이에 본 논문은 태양 에너지를 충전하여 지속적으로 동작할 수 있는 무선 센서 노드의 에너지 충전 및 방전 특성을 모델링하여 무선 센서 노드의 에너지 활용 형태를 예측할 수 있는 이론적 모델을 제안한다. 개선된 모델에 의해 예측된 결과와 실제 무선 센서 노드의 에너지 활용 패턴을 비교 분석함으로써 실제와 유사하게 모델링할 수 있다.

• 전기학회논문지
• /
• 제64권3호
• /
• pp.393-398
• /
• 2015

City or Community-scale Energy Management System(CEMS) is used to reduce the total energy consumed in the city by arranging the energy resources efficiently at the planning stage and controlling them economically at the operating stage. Of the operational functions of the CEMS, generation forecasting of renewable energy resources is an essential feature for the effective supply scheduling. This is because it can develop daily operating schedules of controllable generators in the city (e.g. diesel turbine, micro-gas turbine, ESS, CHP and so on) in order to minimize the inflow of the external power supply system, considering the amount of power generated by the uncontrollable renewable energy resources. This paper is written to introduce numerical models for photo-voltaic power generation prediction based on the weather forecasting information. Unlike the conventional methods using the average radiation or average utilization rate, the proposed models are developed for CEMS applications using the realtime weather forecast information provided by the National Weather Service.