With the improvement of electricity markets,the gradual aggravation of energy shortage and the environment pollution,it is urgent to formulate a new model to precisely satisfy the system demand for energy and reserve....With the improvement of electricity markets,the gradual aggravation of energy shortage and the environment pollution,it is urgent to formulate a new model to precisely satisfy the system demand for energy and reserve.Currently,power system opti-mization dispatching is always formulated as a discrete-time scheduling model.In this paper,we first demonstrate through an example that the upper and lower bounds of spinning reserve offered by a unit,given in the discrete-time model framework as constraints,is unreachable.This causes the problem that the reserve delivery obtained by the discrete-time scheduling model cannot be carried out precisely.From the detailed analysis of the ramp rate constraints,it is proved that the reachable upper and lower bounds of spinning reserve in every period can be expressed as functions of two variables,i.e.,generation level of unit at the start and end of this period.Thus,a new method is provided to calculate the upper and lower bounds of spinning reserve which are reachable in average.Furthermore,a new model based on this proposed method for joint scheduling of generation and reserve is presented,which considers the ability to realize the scheduled energy and reserve delivery.It converts the opti-mization based accurate scheduling for generation and reserve of power system from a continuous-time optimal control prob-lem to a nonlinear programming problem.Therefore,the proposed model can avoid the difficulties in solving a continu-ous-time optimal control problem.Based on the sequential quadratic programming method,numerical experiments for sched-uling electric power production systems are performed to evaluate the model and the results show that the new model is highly effective.展开更多
The forecasting of time-series data plays an important role in various domains. It is of significance in theory and application to improve prediction accuracy of the time-series data. With the progress in the study of...The forecasting of time-series data plays an important role in various domains. It is of significance in theory and application to improve prediction accuracy of the time-series data. With the progress in the study of time-series, time-series forecasting model becomes more complicated, and consequently great concern has been drawn to the techniques in designing the forecasting model. A modeling method which is easy to use by engineers and may generate good results is in urgent need. In this paper, a gradient-boost AR ensemble learning algorithm (AREL) is put forward. The effectiveness of AREL is assessed by theoretical analyses, and it is demonstrated that this method can build a strong predictive model by assembling a set of AR models. In order to avoid fitting exactly any single training example, an insensitive loss function is introduced in the AREL algorithm, and accordingly the influence of random noise is reduced. To further enhance the capability of AREL algorithm for non-stationary time-series, improve the robustness of algorithm, discourage overfitting, and reduce sensitivity of algorithm to parameter settings, a weighted kNN prediction method based on AREL algorithm is presented. The results of numerical testing on real data demonstrate that the proposed modeling method and prediction method are effective.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.60921003,60736027,61174161,60974101)the Spe-cialized Research Fund for the Doctoral Program of Higher Education of China(Grant No.20090121110022)+3 种基金the Fundamental Research Funds for the Central Universities of Xiamen University(Grant Nos.2011121047,201112G018,CXB2011035)the Key Research Project of Fujian Province of China(Grant No.2009H0044)Xiamen University National 211 3rd Period Project of China)(Grant No.0630-E72000)the Natural Sci-ence Foundation of Fujian Province,China(Grant No.2011J05154)
文摘With the improvement of electricity markets,the gradual aggravation of energy shortage and the environment pollution,it is urgent to formulate a new model to precisely satisfy the system demand for energy and reserve.Currently,power system opti-mization dispatching is always formulated as a discrete-time scheduling model.In this paper,we first demonstrate through an example that the upper and lower bounds of spinning reserve offered by a unit,given in the discrete-time model framework as constraints,is unreachable.This causes the problem that the reserve delivery obtained by the discrete-time scheduling model cannot be carried out precisely.From the detailed analysis of the ramp rate constraints,it is proved that the reachable upper and lower bounds of spinning reserve in every period can be expressed as functions of two variables,i.e.,generation level of unit at the start and end of this period.Thus,a new method is provided to calculate the upper and lower bounds of spinning reserve which are reachable in average.Furthermore,a new model based on this proposed method for joint scheduling of generation and reserve is presented,which considers the ability to realize the scheduled energy and reserve delivery.It converts the opti-mization based accurate scheduling for generation and reserve of power system from a continuous-time optimal control prob-lem to a nonlinear programming problem.Therefore,the proposed model can avoid the difficulties in solving a continu-ous-time optimal control problem.Based on the sequential quadratic programming method,numerical experiments for sched-uling electric power production systems are performed to evaluate the model and the results show that the new model is highly effective.
基金supported by the National Natural Science Foundation of China (Grant No. 60974101)Program for New Century Talents of Education Ministry of China (Grant No. NCET-06-0828)
文摘The forecasting of time-series data plays an important role in various domains. It is of significance in theory and application to improve prediction accuracy of the time-series data. With the progress in the study of time-series, time-series forecasting model becomes more complicated, and consequently great concern has been drawn to the techniques in designing the forecasting model. A modeling method which is easy to use by engineers and may generate good results is in urgent need. In this paper, a gradient-boost AR ensemble learning algorithm (AREL) is put forward. The effectiveness of AREL is assessed by theoretical analyses, and it is demonstrated that this method can build a strong predictive model by assembling a set of AR models. In order to avoid fitting exactly any single training example, an insensitive loss function is introduced in the AREL algorithm, and accordingly the influence of random noise is reduced. To further enhance the capability of AREL algorithm for non-stationary time-series, improve the robustness of algorithm, discourage overfitting, and reduce sensitivity of algorithm to parameter settings, a weighted kNN prediction method based on AREL algorithm is presented. The results of numerical testing on real data demonstrate that the proposed modeling method and prediction method are effective.
