Hybridized Intelligent Neural Network Optimization Model for Forecasting Prices of Rubber in Malaysia

Rubber producers,consumers,traders,and those who are involved in the rubber industry face major risks of rubber price fluctuations.As a result,decision-makers are required to make an accurate estimation of the price of rubber.This paper aims to propose hybrid intelligent models,which can be utilized to forecast the price of rubber in Malaysia by employing monthly Malaysia’s rubber pricing data,spanning from January 2016 to March 2021.The projected hybrid model consists of different algorithms with the symbolic Radial Basis Functions Neural Network k-Satisfiability Logic Mining(RBFNN-kSAT).These algorithms,including Grey Wolf Optimization Algorithm,Artificial Bee Colony Algorithm,and Particle Swarm Optimization Algorithm were utilized in the forecasting data analysis.Several factors,which affect the monthly price of rubber,such as rubber production,total exports of rubber,total imports of rubber,stocks of rubber,currency exchange rate,and crude oil prices were also considered in the analysis.To evaluate the results of the introduced model,a comparison has been conducted for each model to identify the most optimum model for forecasting the price of rubber.The findings showed that GWO with RBFNN-kSAT represents the most accurate and efficient model compared with ABC with RBFNNkSAT and PSO with RBFNN-kSAT in forecasting the price of rubber.The GWO with RBFNN-kSAT obtained the greatest average accuracy(92%),with a better correlation coefficient R=0.983871 than ABC with RBFNN-kSAT and PSO with RBFNN-kSAT.Furthermore,the empirical results of this study provided several directions for policymakers to make the right decision in terms of devising proper measures in the industry to address frequent price changes so that the Malaysian rubber industry maintains dominance in the international markets.

Multi-objective capacity allocation optimization method of photovoltaic EV charging station considering V2G

Large-scale electric vehicles(EVs) connected to the micro grid would cause many problems. In this paper, with the consideration of vehicle to grid(V2 G), two charging and discharging load modes of EVs were constructed. One was the disorderly charging and discharging mode based on travel habits, and the other was the orderly charging and discharging mode based on time-of-use(TOU) price;Monte Carlo method was used to verify the case. The scheme of the capacity optimization of photovoltaic charging station under two different charging and discharging modes with V2 G was proposed. The mathematical models of the objective function with the maximization of energy efficiency, the minimization of the investment and the operation cost of the charging system were established. The range of decision variables, constraints of the requirements of the power balance and the strategy of energy exchange were given. NSGA-Ⅱ and NSGA-SA algorithm were used to verify the cases, respectively. In both algorithms, by comparing with the simulation results of the two different modes, it shows that the orderly charging and discharging mode with V2 G is obviously better than the disorderly charging and discharging mode in the aspects of alleviating the pressure of power grid, reducing system investment and improving energy efficiency.

A Multimodel Transfer-Learning-Based Car Price Prediction Model with an Automatic Fuzzy Logic Parameter Optimizer

Cars are regarded as an indispensable means of transportation in Taiwan.Several studies have indicated that the automotive industry has witnessed remarkable advances and that the market of used cars has rapidly expanded.In this study,a price prediction system for used BMW cars was developed.Nine parameters of used cars,including their model,registration year,and transmission style,were analyzed.The data obtained were then divided into three subsets.The first subset was used to compare the results of each algorithm.The predicted values produced by the two algorithms with the most satisfactory results were used as the input of a fully connected neural network.The second subset was used with an optimization algorithm to modify the number of hidden layers in a fully connected neural network and modify the low,medium,and high parameters of the membership function(MF)to achieve model optimization.Finally,the third subset was used for the validation set during the prediction process.These three subsets were divided using k-fold cross-validation to avoid overfitting and selection bias.In conclusion,in this study,a model combining two optimal algorithms(i.e.,random forest and k-nearest neighbors)with several optimization algorithms(i.e.,gray wolf optimizer,multilayer perceptron,and MF)was successfully established.The prediction results obtained indicated a mean square error of 0.0978,a root-mean-square error of 0.3128,a mean absolute error of 0.1903,and a coefficient of determination of 0.9249.

一种基于新改进的Price算法的混合遗传算法求解约束优化问题

新改进的Price算法能够求解多峰、多维,以及不可微目标函数的全局优化问题。把新改进的Price算法作为局部搜索算子,并入到实数编码遗传算法中,构成一个混合遗传算法,求解约束优化问题。该混合算法增强了全局寻优能力,提高了函数值的精度,并减少了计算量。通过对13个约束标准测试函数的仿真实验,并和已有算法的比较,结果表明本文提出的混合遗传算法是有效的。

Chaotic Optimal Operation of Hydropower Station with Ecology Consideration

Traditional optimal operation of hydropower station usually has two problems. One is that the optimal algorithm hasn’t high efficiency, and the other is that the optimal operation model pays little attention to ecology. And with the development of electric power market, the generated benefit is concerned instead of generated energy. Based on the analysis of time-varying electricity price policy, an optimal operation model of hydropower station reservoir with ecology consideration is established. The model takes the maximum annual power generation benefit, the maximum output of the minimal output stage in the year and the minimum shortage of eco-environment demand as the objectives, and reservoir water quantity balance, reservoir storage capacity, reservoir discharge flow and hydropower station output and nonnegative variable as the constraints. To solve the optimal model, a chaotic optimization genetic algorithm which combines the ergodicity of chaos and the inversion property of genetic algorithm is exploited. An example is given, which shows that the proposed model and algorithm are scientific and feasible to deal with the optimal operation of hydropower station.

高速铁路列车开行方案与票价票额综合优化

为提升高速铁路的运营组织水平和盈利能力,本文提出高铁列车开行方案与票价票额综合优化方法。首先,构建分时客流需求与票价间弹性需求函数,并分析包括出发时段偏差、乘车耗时及票价的旅客广义出行成本,进而采用多项式Logit模型描述分时弹性客流的列车选择行为。在此基础上,以客票总收入与运营总成本之差最大为目标构建三者综合优化模型。其次,利用OD总收益关于列车票价的偏导构造票价方案搜索策略,使票价邻域解和列车开行方案邻域解相适应,并运用Cplex求解对应的最优票额分配方案,设计模拟退火算法求解模型。最后,基于郑西高速铁路进行算例分析,结果表明:在7个不同弹性系数下进行综合优化,旅客出行成功率和列车平均客座率均在90%以上,优化解的列车开行方案、票价方案及票额分配方案均高度匹配;在5组不同规模算例中,三者综合优化的运营净收益相比于固定票价下的开行方案与票额联合优化和固定开行方案下的票价与票额联合优化,分别提高了4.11%~15.25%和3.17%~13.42%,且人均单位里程出行成本亦分别降低了1.69%~4.96%和0.97%~4.35%,表明综合优化更好地提升了高速铁路的运营收益和旅客服务水平。

基于模糊次梯度算法的分布式智能电网实时定价策略

实时定价是智能电网需要研究的关键问题之一,社会福利最大化方法是研究分布式智能电网实时定价的重要方法。从电网系统的整体效益出发,兼顾供需双方利益,建立社会福利最大化的定价模型。在模型求解中,首先,基于对偶理论,将所建模型的求解转化为其对偶问题的求解;其次,求解对偶问题,针对次梯度算法易出现振荡、求解效率低的问题,利用历史次梯度信息对传统次梯度算法进行改进,且基于模糊理论,采用隶属度函数确定迭代中历史次梯度的权重系数;最后,给出一个新的分布式实时定价算法。求解过程中,通过用电数据信息和供电数据信息的实时交互,获得实时电价,以及所有用户的用电量、供电商的供电量。数值仿真验证了所建定价模型的合理性以及给出的分布式算法的有效性。

动态价格约束下生鲜无人零售点选址-路径方法研究

“新零售”创新了生鲜无人零售的渠道和销售模式,通过研究网络化无人售货的技术优势,引入在线动态定价机制,解决了生鲜无人销售品控难、客户黏度低的问题,有效减低了系统综合成本;同时构建了一种面向生鲜商品的无人零售的干线和支线混杂配送模型,在多目标求解、问题解耦和PSO全局优化等方面进行突破,建立了一种动态价格约束下的带时间窗选址-路径二级运输模型(2E-dPLRPTW),并进行了案例验算,确认该方法能有效提升生鲜商品无人售卖的效益。

考虑出库不确定性的船舶舾装件立库入库优化

针对船舶舾装件立体仓库入库货位分配优化问题,本文建立了以货架稳定原则、齐配就近原则以及出库速度最快原则为优化目标的多目标优化模型。实现了考虑船舶出库不确定特点且兼顾托盘齐配率提升的立库入库优化。该研究通过分布式鲁棒优化解决了由于舾装件种类多、标准化程度低等特点导致的出库频率分布难以通过历史数据进行准确刻画的问题。基于模型的数学结构对模型进行分解,并研究设计了使用遗传算法进行热启动的分支定价算法。克服了启发式算法无法获得精确解、传统优化算法求解时间过长的两大难题,实现了大规模问题的快速精确求解,并通过数值实验结果表明:该模型对舾装件入库货位分配具有明显的优化效果。

一种基于电量聚类分析的居民阶梯电价制定方法

我国居民用电执行阶梯电价政策。针对现有阶梯电价制定方法存在的不足,采用基于电力大数据的分析思想,形成一种新的阶梯电价制定方法。首先介绍用电量数据的结构特点和k-means++算法的基本原理,将聚类结果作为测算,验证了该方法的优越性。

计及购电需求不确定性的微电网能源竞价交易模型

微电网可以将发电高峰期盈余的可再生能源出售来促进可再生能源消纳并获取最大收益。采用拍卖机制确定交易价格,但交易过程中购电需求的变化也会对可再生能源消纳及微电网收益产生影响,为此,提出一种计及购电需求不确定性的微电网能源竞价交易模型。首先采用统一价格同步向上叫价拍卖机制进行定价,并提出了拍卖机制的改进方案来平衡用能消费者的对不同时段的拍卖需求;考虑到用能消费者的购电需求不确定性,采用鲁棒线性优化算法来规避不确定性参数对最优解的影响。最后通过MATLAB软件仿真分析,证明了该模型能够最大限度地提高可再生能源的出售率及微电网的收益。

计及配电网灵活性的峰谷电价分布鲁棒定价策略

高比例可再生能源接入加剧了配电网的不确定性,亟需利用分时电价激励用户参与需求响应,对负荷侧灵活性资源进行挖掘。为此,提出计及配电网灵活性的峰谷电价分布鲁棒定价策略。利用价格弹性矩阵量化用户响应分时电价的行为,并基于Wasserstein距离构建光伏出力与负荷预测误差区间的分布鲁棒不确定集;采用区间法对配电网灵活性供给与需求进行建模,并构建灵活性评估指标;建立综合考虑用户用电方式满意度、净负荷峰谷差、灵活性供需平衡的分布鲁棒定价模型,并采用混合优化算法进行模型求解。算例结果验证了所提分布鲁棒定价策略的有效性与鲁棒性。

基于麻雀搜索优化SVR模型的房地产价格研究

为解决传统经济指标作为房价影响因素的数据获取滞后性问题以及机器学习模型在预测房价时存在的参数选取不确定性问题,文中以网络搜索数据作为房价指数解释变量,采用麻雀搜索算法(Sparrow Search Algorithm,SSA)建立SSA-SVR(Support Vector Regression)模型对SVR的惩罚因子C和RBF(Radical Basic Function)核函数的参数g进行优化。将SSA-SVR模型与PSO(Particle Swarm Optimization)-SVR、GA(Genetic Algorithm)-SVR、WOA(Whale Optimization Algorithm)-SVR、GS(Grid Search)-SVR以及基准SVR进行对比,SSA-SVR的相关系数(0.99)、均方根误差(6.71)、平均绝对误差(5.24)、均方误差(45.13)以及平均绝对百分比误差(0.26%)均优于其他5种模型。结果表明,麻雀搜索算法优化的SVR模型在房价预测方面具有更好的全局寻优能力,可以提高模型的预测准确度和预测能力。

基于参数优化VMD与XGBoost算法的玉米蛋白粉价格预测

玉米蛋白粉价格稳定对饲料工业可持续发展和国家粮食安全具有重要意义,但其价格序列具有非平稳、非线性特征,难以精确预测。试验旨在基于XGBoost算法,构建玉米蛋白粉价格预测模型。首先,利用鲸鱼算法(WOA)优化变模分解(VMD)的K值和惩罚参数,对原始价格序列进行自适应分解,降低数据噪声。其次,将Pearson特征筛选后的变量作为极限梯度提升树(XGBoost)模型的输入,进行训练和测试。最后,使用10折交叉验证和学习曲线检验模型性能,并结合SHAP模型分析关键影响因素的非线性效应。结果显示,上一期豆粕期货价格对本期玉米蛋白粉价格波动具有显著的正向影响。研究表明,贝叶斯算法(BO)优化的XGBoost模型具有较好的预测性能,优于基准模型。

可解释性分层神经模糊网络的股票价格预测算法

针对现有的股票价格预测模型难以兼顾精度与可解释性的问题,提出一种基于分层神经模糊网络的股票价格预测模型。提出一种结合注意力机制的自适应神经模糊网络单元(ANFIS-A),以此单元构建分层自适应神经模糊网络;结合二进制灰狼优化算法(BGWO),提出一种特征子集选择算法;提出一种规则消除的递归算法,进一步减少规则数量,提高规则的可解释性。实验结果表明,该模型在预测股票价格方面具有较高的准确性和可解释性。

一种基于改进VMD-PSO-CNN-LSTM的短期电价预测方法

为了提升电价预测的准确性和预测模型的稳定性,提出一种基于改进VMD-PSO-CNN-LSTM的短期电价预测方法。首先,通过研究变分模态分解(variational mode decomposition,VMD)与电价影响因素的相关影响程度,并引入最大信息系数(MIC)构建VMD参数优化模型;然后,利用卷积神经网络(convolutional neural networks,CNN)与长短期记忆(long short-term memory,LSTM)神经网络对VMD分解得到的各模态分量进行预测。同时,根据深度可分离卷积结合电价时间规律,在CNN卷积部分构建多尺度的卷积特征提取结构,并利用粒子群优化算法优化包括CNN卷积层数量、CNN卷积神经元数量、LSTM隐藏层数量、LSTM记忆时间以及全连接层数等在内的参数,从而实现模型预测准确性和稳定性的提升。最后,对澳洲电力市场日前电价进行分析预测并与对照算法对比,结果表明该文算法具有更高的精度和更好的稳定性。

考虑EV车主需求的风-火-储联合调度多目标优化策略

风电出力的波动性和电动汽车充放电的无序性增加了电力系统调度的负担,因此,电力系统在发电侧需考虑各资源的分配,用户侧需合理安排电动汽车有序参与电网调度。针对此问题,建立考虑电动汽车车主需求的风-火-储联合调度多目标优化模型。以净负荷方差、系统运行总成本和车主支付费用最低为目标,通过设立不同的分时电价引导车主参与电网调度。采用NAGA-Ⅱ算法和模糊层次分析法求得帕雷托解集中的最优解。结果表明:策略能够有效地减少系统净负荷方差、平抑系统波动,同时减少系统的总运行成本和车主的支付费用;不同的分时电价标准对于电动汽车参与调度的影响不同。

基于双层优化的电动车与电网实时协同定价机制

电动车充电行为的非完全竞争性和不完全信息性,以及电力系统的非线性和不确定性,导致电网实时定价问题的建模和求解及其复杂。现有解决方案往往将其建模为一个带约束的优化问题,并且认为效用函数对于电网是已知的,忽略了现实中存在的信息不完全性。为了克服这一局限,在效用函数参数未知的情况下,提出了一种基于双层优化的电动车与电网实时协同定价机制。该机制的创新性在于能够更好地反映电动车充电市场的真实动态;同时,引入电网的潮流方程来反映电网的实时负载。在该模型中,上层模型最大化电网供电商的收益,同时尽可能减小电网的负载压力;下层模型优化电动车充电行为,每一辆电动车的目标是最小化自身的充电成本。通过与固定电价以及峰谷电价情况进行对比,实验仿真数据揭示了所提机制能够更好地平衡电网以及电动车的收益并且增加两者总收益,同时减小电网的负载。

计及虚拟电厂内需求侧灵活性资源的实时电价和V2G协调优化调度策略

制定合理有效的电价策略和电动汽车充放电策略,可以为电网的经济稳定运行提供保障。文章综合考虑负荷用户、虚拟电厂运营商和上层电网利益,建立了以平抑净负荷功率波动为目标的价格型需求响应实时电价模型,通过引入多种群交互、模拟退火、最优个体扰动等机制对粒子群算法进行改进,并利用算法进行求解得到实时电价方案;然后结合住宅区电动汽车时移特性,在虚拟电厂两日的经济调度时间尺度上,考虑虚拟电厂和电动汽车用户利益建立优化调度模型。算例分析表明所述策略提高了虚拟电厂运行的稳定性、经济性,减少了与上层电网的平均交互电量和峰谷差。

考虑参考价格效应的库存路径与定价问题

针对客户有价格策略型行为下的供应商库存路径与定价问题(inventory routing and pricing problem,IRPP),通过将参考价格效应嵌入产品需求价格函数中,以供应商总利润最大化为目标,构建考虑参考价格效应的IRPP优化模型,设计改进的粒子群算法进行求解。通过3组不同规模的算例验证本文模型与算法的适用性和有效性。计算结果显示,考虑参考价格效应不仅有助于降低产品定价(约9%)和提升客户感知收益,而且能够降低零售商的产品总库存(约22%)、仓储资源占用成本和库存持有成本,从而提高供应商总利润(约5%)。敏感性分析结果显示:受客户记忆参数减小和增益系数增大的共同影响,供应商总利润会明显增加;受客户记忆参数和损失系数增大的共同影响,供应商总利润会迅速下降。研究结论可为电商环境下客户有价格策略型行为下的供应商IRPP优化提供决策支撑。