Load forecasting has received crucial research attention to reduce peak load and contribute to the stability of power grid using machine learning or deep learning models.Especially,we need the adequate model to foreca...Load forecasting has received crucial research attention to reduce peak load and contribute to the stability of power grid using machine learning or deep learning models.Especially,we need the adequate model to forecast the maximum load duration based on time-of-use,which is the electricity usage fare policy in order to achieve the goals such as peak load reduction in a power grid.However,the existing single machine learning or deep learning forecasting cannot easily avoid overfitting.Moreover,a majority of the ensemble or hybrid models do not achieve optimal results for forecasting the maximum load duration based on time-of-use.To overcome these limitations,we propose a hybrid deep learning architecture to forecast maximum load duration based on time-of-use.Experimental results indicate that this architecture could achieve the highest average of recall and accuracy(83.43%)compared to benchmark models.To verify the effectiveness of the architecture,another experimental result shows that energy storage system(ESS)scheme in accordance with the forecast results of the proposed model(LSTM-MATO)in the architecture could provide peak load cost savings of 17,535,700 KRW each year comparing with original peak load costs without the method.Therefore,the proposed architecture could be utilized for practical applications such as peak load reduction in the grid.展开更多
The present paper proposes the impact of the air temperature on electricity demand as expected. The annual maximum load is recorded versus the years starting by the year 2009. At present, the graph fitting was applied...The present paper proposes the impact of the air temperature on electricity demand as expected. The annual maximum load is recorded versus the years starting by the year 2009. At present, the graph fitting was applied with some mathematical and computational tools considering the lower values, the higher values and the average values of the annual maximum loads of Kingdom of Bahrain. For the three scenarios, the models are obtained by curve fitting technique. As well, the model of actual loads is obtained finally which has mostly the closest values obtained.展开更多
To simplify the calculation of the maximum load at which instability occurs for reinforced-concrete pipe columns under eccentric compression, a method based on the transformed cross-sectional area of the column and th...To simplify the calculation of the maximum load at which instability occurs for reinforced-concrete pipe columns under eccentric compression, a method based on the transformed cross-sectional area of the column and the concrete secant modulus of elasticity is proposed, consisting of an iterative process in which a sequence of lateral deflections is at column mid-height. The method assumes the deflected shape of the column as a half cosine wave. Analytical results were compared with experimental values obtained from 16 reinforced-concrete pipe columns. Using deflection at column mid-height recorded during the loading proc-ess, a typical load-deflection curve can be plotted and used to describe column behavior. The experimental results demonstrate that the failure of concrete columns is a process. The starting point is the cracking load point, when cracks are initiated in the concrete of the tensile zone of the critical cross-section of specimens. The maximum load point is the top of the failure process, and then the maximum bending moment occurs. The first point represents instability while the second one corresponds to the strength failure of the columns. The experimental results are close to the analytical values. The method is simple and can be used for stabil-ity analysis of reinforced-concrete pipe columns.展开更多
Total pollutant load control management for total dissolved nitrogen(TDN) is an urgent task required to gain a good water quality status in Jiaozhou Bay(JZB), China. In this paper, the stoichiometry of multiform TDN o...Total pollutant load control management for total dissolved nitrogen(TDN) is an urgent task required to gain a good water quality status in Jiaozhou Bay(JZB), China. In this paper, the stoichiometry of multiform TDN on land-ocean interactions associated with marine biogeochemical reaction(LOIMBR) was studied by modeling the load-response relationship based on a three-dimensional water quality model of nitrogen in JZB. The results showed that the stoichiometry on LOIMBR of dissolved organic nitrogen(DON), NO3-N and NH4-N was 3:1:1, with one-third of the contribution on the concentration of dissolved inorganic nitrogen(DIN) in JZB for the land-based DON loads to DIN loads. Based on the stoichiometric relationship of nitrogen forms, the total maximum allocated load(TMAL) of equivalent TDN(ETDN) was approximately 5300 t a^-1 in JZB, equivalent to the TMAL of 5700, 5800 and 15600 t a^-1 for NH4-N, NO3-N and DON, respectively. According to the loads of ETDN, there were four outfalls overloaded in JZB in 2015, which lie in the head of the bay. In the four overloaded outfalls, besides NO3-N, NH4-N was the critical nitrogen control form for Moshui River, while DON for Dagu River and Haibo River. The results of numerical experiments further showed that JZB will achieve good water quality after 7 years by implementation of the 'different emission reduction' based on TMAL of ETDN, which is significantly better than 'equal percent removal'.展开更多
基金supported by Institute for Information&communications Technology Planning&Evaluation(IITP)funded by the Korea government(MSIT)(No.2019-0-01343,Training Key Talents in Industrial Convergence Security)Research Cluster Project,R20143,by Zayed University Research Office.
文摘Load forecasting has received crucial research attention to reduce peak load and contribute to the stability of power grid using machine learning or deep learning models.Especially,we need the adequate model to forecast the maximum load duration based on time-of-use,which is the electricity usage fare policy in order to achieve the goals such as peak load reduction in a power grid.However,the existing single machine learning or deep learning forecasting cannot easily avoid overfitting.Moreover,a majority of the ensemble or hybrid models do not achieve optimal results for forecasting the maximum load duration based on time-of-use.To overcome these limitations,we propose a hybrid deep learning architecture to forecast maximum load duration based on time-of-use.Experimental results indicate that this architecture could achieve the highest average of recall and accuracy(83.43%)compared to benchmark models.To verify the effectiveness of the architecture,another experimental result shows that energy storage system(ESS)scheme in accordance with the forecast results of the proposed model(LSTM-MATO)in the architecture could provide peak load cost savings of 17,535,700 KRW each year comparing with original peak load costs without the method.Therefore,the proposed architecture could be utilized for practical applications such as peak load reduction in the grid.
文摘The present paper proposes the impact of the air temperature on electricity demand as expected. The annual maximum load is recorded versus the years starting by the year 2009. At present, the graph fitting was applied with some mathematical and computational tools considering the lower values, the higher values and the average values of the annual maximum loads of Kingdom of Bahrain. For the three scenarios, the models are obtained by curve fitting technique. As well, the model of actual loads is obtained finally which has mostly the closest values obtained.
基金Supported by the Chinese Scholarship Council of the Educa-tion Ministry and National Key Basic Research and Devel-opment (973) Program of China (No. 2002CB412709)
文摘To simplify the calculation of the maximum load at which instability occurs for reinforced-concrete pipe columns under eccentric compression, a method based on the transformed cross-sectional area of the column and the concrete secant modulus of elasticity is proposed, consisting of an iterative process in which a sequence of lateral deflections is at column mid-height. The method assumes the deflected shape of the column as a half cosine wave. Analytical results were compared with experimental values obtained from 16 reinforced-concrete pipe columns. Using deflection at column mid-height recorded during the loading proc-ess, a typical load-deflection curve can be plotted and used to describe column behavior. The experimental results demonstrate that the failure of concrete columns is a process. The starting point is the cracking load point, when cracks are initiated in the concrete of the tensile zone of the critical cross-section of specimens. The maximum load point is the top of the failure process, and then the maximum bending moment occurs. The first point represents instability while the second one corresponds to the strength failure of the columns. The experimental results are close to the analytical values. The method is simple and can be used for stabil-ity analysis of reinforced-concrete pipe columns.
基金supported by the National Natural Science Foundation of China (No.41676062)the NSFC-Shandong Joint Fund for Marine Ecology and Environmental Sciences (No.U1606404)+1 种基金the Key R&D Program of Shandong (No.2018GHY115005)the NSFC-Shandong Joint Fund (No.U1706215)。
文摘Total pollutant load control management for total dissolved nitrogen(TDN) is an urgent task required to gain a good water quality status in Jiaozhou Bay(JZB), China. In this paper, the stoichiometry of multiform TDN on land-ocean interactions associated with marine biogeochemical reaction(LOIMBR) was studied by modeling the load-response relationship based on a three-dimensional water quality model of nitrogen in JZB. The results showed that the stoichiometry on LOIMBR of dissolved organic nitrogen(DON), NO3-N and NH4-N was 3:1:1, with one-third of the contribution on the concentration of dissolved inorganic nitrogen(DIN) in JZB for the land-based DON loads to DIN loads. Based on the stoichiometric relationship of nitrogen forms, the total maximum allocated load(TMAL) of equivalent TDN(ETDN) was approximately 5300 t a^-1 in JZB, equivalent to the TMAL of 5700, 5800 and 15600 t a^-1 for NH4-N, NO3-N and DON, respectively. According to the loads of ETDN, there were four outfalls overloaded in JZB in 2015, which lie in the head of the bay. In the four overloaded outfalls, besides NO3-N, NH4-N was the critical nitrogen control form for Moshui River, while DON for Dagu River and Haibo River. The results of numerical experiments further showed that JZB will achieve good water quality after 7 years by implementation of the 'different emission reduction' based on TMAL of ETDN, which is significantly better than 'equal percent removal'.
