基于DGM的模糊多目标区间预测

无论对预测过程还是决策过程,区间预测相对于点估计预测往往拥有更重要的信息量。本文基于模糊多目标规划模型和离散灰色模型理论(DGM),给出了基于DGM的模糊多目标区间预测模型。同时,为了有利于比较区间预测的优劣,又提出了评价区间预测优劣的两个指标:区间中心的均值相对百分比误差和区间边界的均值相对百分比误差。最后,将LCD TV销售量作为本模型的实验数据,给出了区间预测的结果,并将我们的结果与其他两个模型的预测结果进行了比较分析。     

基于预测精度的多目标组合预测优化模型研究

考虑了组合预测精度的数学期望和预测精度的标准差这两个指标 ,建立了多目标规划组合预测最优化模型 ,并给出其数学规划的解法 .最后进行实例分析 ,结果令人满意 .该模型能反映不同时间序列预测方法有效性     

改进的灰色模型及在短时交通流中的应用

基于城市道路交通流按日周期变化的数据特征,提出一种可自动选择步长的灰色模型算法.将其应用到美国Minnesota的两个道路交通流的预测,并和传统灰色模型、历史平均法以及滑动平均法对比.数值实验结果表明:改进的灰色模型能够大幅降低预测绝对误差,预测精度高,稳定性好,适用于城市道路短时交通流的实时预测.     

基于XGBoost-LSTM模型的多特征股票价格预测研究

为探寻股票价格规律,提出XGBoost与LSTM组合的股票价格预测模型,选取恒瑞医疗股票2000年10月18日上市至2022年9月1日所有交易日的交易数据为实证分析对象.首先,建立单特征与多特征LSTM模型分别对股票价格进行预测;其次,构建XGBoost模型以进一步实现预测并将预测结果作为新变量输入到多特征LSTM模型;然后,使用LSTM模型在新数据集上进行建模;最后,对比分析表明多特征LSTM模型预测效果优于单特征预测,XGBoost-LSTM预测模型效果优于多特征LSTM预测,说明本文提出的方法能进一步提升预测效果,对投资者有一定参考价值.     

到点式服务模式电动汽车电池需求预测

针对电动汽车充电难这一现状,分析现有的电动汽车充换电模式特点,结合电动汽车服务"通用化、智能化"趋势,提出了换电站到点式服务模式.分析到点式服务模式下用户的需求分布特点,建立灰色预测模型对电动汽车保养量进行预测,利用汽车保有量与电池关系来预测电池需求量,作为换电站电池配依据.最后,选取北京的相关数据进行分析,验证了模型的可行性与有效性.     

城市道路短时交通流量预测

结合BP神经网络模型和自回归求和滑动平均(ARIMA)模型对城市道路交通短时区间流量进行预测.影响交通流的因素有很多,难以一一量化,但这些因素都可以由线性自相关结构和非线性结构结合线性组合得到.而BP神经网络对非线性关系有很好的拟合效果,ARIMA模型则具有良好的线性拟合能力.在训练模型时,先用ARIMA模型拟合训练集,与原始数据作差得到一组残差;用BP神经网络模型拟合残差;将两个模型结合得到组合模型.将2017年7月1日7:00到2017年7月1日18:00期间,贵阳市某个路口断面所采集的过车数据作为训练集,建立ARIMA模型和BP神经网络模型以及组合模型,预测2017年7月1日18:00到2017年7月1日19:00的短时交通流.过车数据统计时间间隔为5min,则训练集共有有效数据132组,测试集的有效数据为12组.分别用三类误差分析指标比较三个模型的拟合、预测效果,结果显示组合模型的预测效果比两个模型单独使用的预测效果更准确.     

梯级水库群防洪系统多目标决策的灰色优选

将传统的优化技术与新发展起来的灰关联决策理论有机地结合起来,针对洪水调度的特点,提出了一个切实可行的梯级水库群洪水调度方案决策的灰色优选模型.最后,以乌江流域4个梯级电站的洪水调度方案优选进行了说明.     

自适应AR模型用于世界时序列的预测

世界时的预测可分为确定性成分的预测和随机性成分的预测两个部分。本文采用NEOS两年期间每天的UT1-UTC资料,用线性拟合外推和周期拟合外推方法预测世界时序列的确定性成分;用自适应AR模型的RLS递推算法预测世界时序列的随机性成分,综合两个部分的结果,获得较好的预测效果。步长为60d的预测精度达到0^s.0038。     

多因子概率综合长期预测模型

对危害农作物生长的病虫害进行预测预报，其预报一般分短期、中期、长期、补充和警报五种．发布５日以外，１０日以内的病虫预报称为短期预报．发布１０日以外，一个月以内的病虫预报称为中期预报．发布一个月以外病虫发生趋势的预报（包括年预报）称为长期预报．本文提出一个年预报的模型．它是在笔者从事三年多的病虫预报实践中组建出来的．利用这个模型，对安徽省蒙城县小麦粘虫一代工龄幼虫的发生密度预测获得成功，历史准确率达９２． ８６％．对该县８８年幼虫密度也给出了预报．     

具有离散参数齐次随机场的线性预测（IX）

研究了14平面的线性预测及14平面上观察时存在遗漏观察值的线性预测,并得到了这两个预测问题之间的预测误差、预测值的对应关系.     

Dynamic loading of layered composite beams with damage of delamination type

Failure of composite beams containing initial delamination is investigated under low-speed impact by a dropping weight. Bolotin's theory of dynamic failure (1992) is used. The start and stop time of growth of a nonsymmetric delamination crack is studied. It is found that the initial extension starts and subsequently continues at the crack tip, which is located closer to the impact point. Then extension is observed on the second crack tip, and finally a synchronous growth of delamination occurs at both crack tips. With constant impact energy, the final size of delamination does not depend on its initial size. The start and stop time of delamination growth increases as the initial defect approaches the beam surface.Presented at the 10th International Conference on the Mechanics of Composite Materials (Riga, April 20–23, 1998).Moscow Power Engineering Institute, Technical University, Russia. Translated from Mekhanika Kompozitnykh Materialov, Vol. 34, No. 6, pp. 787–794, November–December, 1998.     

Optimal electricity production from hydro power plants with storage

This paper integrates aspects of depletion and inventory control models to investigate optimal production from hydro-reservoirs. Power stations with storage attempt to transfer electricity production from the high supply (summer) to the high demand (winter) season. This paper is motivated by the Austrian hydrothermal system of power plants and the adverse supply of hydro power. The paper considers two institutional frameworks: A monopoly, which sells electricity to the integrated electricity network; a welfare optimal utilization of electricity from annual hydro storage plants. The electricity supplied from annual storage reservoirs are utilized in both cases to substitute for electricity generated in those (thermal) power plants which produce inefficiently at the offered price. The theoretical framework is empirically applied to Austrian data.

---

Zusammenfassung Diese Arbeit analysiert die jährliche optimal Speicherbewirtschaftung für österreichs Elektrizitätswirtschaft, die auf einem hohen Anteil an Wasserkraft und residualer thermischer Erzeugung fußt. Langzeitspeicher, sogenannte Jahresspeicher, ergeben die Möglichkeit, Elektrizität aus dem regenreichen Sommer in den trockenen Winter mit hoher Nachfrage zu transferieren. Eine Integration und entsprechende Adaption von Modellen der Lagerhaltung und Ressourceausbeutung beschreibt die dynamischen und saisonalen Komponenten des Problems. Dabei werden zwei institutionelle Rahmenbedingungen behandelt: ein Monopol und ein wohlfahrtsorientiertes Management verwalten Österreichs (aggregierten) Speichersee. Diese Modelle werden sowohl theoretisch analysiert als auch empirisch auf die österreichische Situation angewandt.

---

---

The author acknowledges the support of Thomas Lemmerer and Erwin Mair in compiling the data for the empirical application. The comments and suggestions from the editor and the anonymous referees proved also helpful. Off course, the usual disclaimer applies.     

基地化保障模式下飞机四站装备需求确定研究

基地化保障模式对飞机保障资源需求的影响是制约其发展的重要问题.基于离散事件仿真(DES)方法建立了航空兵场站四站保障过程的数学模型,考虑了四站装备自身故障的影响,并在所建模型的基础上提出运用离散系统仿真软件ARENA对四站保障过程进行仿真.仿真结果表明,与现行的航空兵场站单机种保障策略相比,基地化保障模式能够减少各个机种通用的四站装备数量需求,而单个机种特有的四站装备需求不变.     

A stochastic model for the daily coordination of pumped storage hydro plants and wind power plants

We propose a stochastic model for the daily operation scheduling of a generation system including pumped storage hydro plants and wind power plants, where the uncertainty is represented by the hourly wind power production. In order to assess the value of the stochastic modeling, we discuss two case studies: in the former the scenario tree is built so as to include both low and high wind power production scenarios, in the latter the scenario tree is built on historical wind speed data covering a time span of one and a half year. The Value of the Stochastic Solution, computed by a modified new procedure, shows that in scenarios with low wind power production the stochastic solution allows the producer to obtain a profit which is greater than the one associated to the deterministic solution. In-sample stability of the optimal function values for increasing number of scenarios is reported.     

Closest 4-leaf power is fixed-parameter tractable

The NP-complete Closest 4-Leaf Power problem asks, given an undirected graph, whether it can be modified by at most r edge insertions or deletions such that it becomes a 4-leaf power. Herein, a 4-leaf power is a graph that can be constructed by considering an unrooted tree—the 4-leaf root—with leaves one-to-one labeled by the graph vertices, where we connect two graph vertices by an edge iff their corresponding leaves are at distance at most 4 in the tree. Complementing previous work on Closest 2-Leaf Power and Closest 3-Leaf Power, we give the first algorithmic result for Closest 4-Leaf Power, showing that Closest 4-Leaf Power is fixed-parameter tractable with respect to the parameter r.     

Optimal operation for a bi-fuel thermal power plant by mathematical programming

This study is an attempt to provide the management of the Electricity Generating Authority of Thailand with an effective tool for determining the best operation of thermal units. A bi-fuel thermal power plant at North Bangkok, consisting of three thermal units, is considered. One of these units is adaptable to both lignite and fuel oil use, while the others use only fuel oil. A general optimization model, applicable to most power plants, is developed and a simplified version is applied to the North Bangkok Power Plant. A 0–1 mixed integer linear programming technique is used to find a method of operating the thermal units, which minimizes total fuel costs. Comparing the optimal solutions with actual operating strategies shows that savings in costs can be realised by implementing the model solution. Moreover, since the framework developed is quite general, it may be usefully applied to other power plant studies.     

The flow shop problem with time lags and separated setup times

This paper generalizes Khurana-Bagga's flow-shop model which involves separated setup times and time lags where no restrictions are imposed on the processing and setup times as well as start and stop lags. It solves the two machine case and provides and approximate solution for the multimachine case. It also shows that Khurana-Bagga's algorithm is restricted to a special case of the two machine problem.     

An efficient linear model and optimisation algorithm for multi-site combined heat and power production

Combined heat and power (CHP) production is an important energy production technology which can help to improve the efficiency of energy production and to reduce the emission of CO₂. Cost-efficient operation of a CHP system can be planned using an optimisation model based on hourly load forecasts. A long-term planning model decomposes into hourly models, which can be formulated as linear programming (LP) problems. Such problems can be solved efficiently using the specialized Power Simplex algorithm. However, Power Simplex can only manage one heat and one power balance. Since heat cannot be transported over long distances, Power Simplex applies only for local CHP planning.In this paper we formulate the hourly multi-site CHP planning problem with multiple heat balances as an LP model with a special structure. We then develop the Extended Power Simplex (EPS) algorithm for solving such models efficiently. Even though the problem can be quite large as the number of demand sites increases, EPS demonstrates very good efficiency. In test runs with realistic models, EPS is from 29 to 85 times faster than an efficient sparse Simplex code using the product form of inverse (PFI). Furthermore, the relative efficiency of EPS improves as the problem size grows.     

Adaptive filter for systems with unknown noise covariances using an instrumental performance functional

An original approach is proposed to constructing algorithms that estimate the unknown model parameters and the state vector of a linear dynamic system using an instrumental performance functional that leads to algorithms with a built-in start/stop rule. The particular case of a nonsingular observation matrix is considered in detail, as it is often observed in applied problems. The theoretical algorithm is presented in two versions that can be used in practice. Some practical recommendations concerning the implementation and application of the algorithm are offered. Translated from Algoritmy Upravleniya i Identifikatsii, pp. 26–39, 1997.     

Multi-Skilled Workforce Optimisation

This paper describes a problem faced by CS Energy's Swanbank Power Station in the Australian state of Queensland. It involved the personnel scheduling (rostering) of staff with multiple skill levels at the power station. Such a problem can be classified using the six stage construction process proposed by Ernst et al. We assume that the three processes of ‘demand modelling,’ ‘shift starting times’ and ‘task scheduling’ are specified. We are concerned with the essential processes of ‘day off scheduling,’ ‘line of work construction’ and ‘shift assignment to staff’ with requirements to maintain multiple skills. Several other authors have reported results for staff with hierarchical skills while the methods proposed in this paper are for non-hierarchical skill sets. The paper describes a set covering approach to the multi-skilled rostering problem. We propose a number of solution strategies for the set covering approach and give a comparison of the results.