Long-Term Electrical Load Forecasting in Rwanda Based on Support Vector Machine Enhanced with Q-SVM Optimization Kernel Function

In recent years, Rwanda’s rapid economic development has created the “Rwanda Africa Wonder”, but it has also led to a substantial increase in energy consumption with the ambitious goal of reaching universal access by 2024. Meanwhile, on the basis of the rapid and dynamic connection of new households, there is uncertainty about generating, importing, and exporting energy whichever imposes a significant barrier. Long-Term Load Forecasting (LTLF) will be a key to the country’s utility plan to examine the dynamic electrical load demand growth patterns and facilitate long-term planning for better and more accurate power system master plan expansion. However, a Support Vector Machine (SVM) for long-term electric load forecasting is presented in this paper for accurate load mix planning. Considering that an individual forecasting model usually cannot work properly for LTLF, a hybrid Q-SVM will be introduced to improve forecasting accuracy. Finally, effectively assess model performance and efficiency, error metrics, and model benchmark parameters there assessed. The case study demonstrates that the new strategy is quite useful to improve LTLF accuracy. The historical electric load data of Rwanda Energy Group (REG), a national utility company from 1998 to 2020 was used to test the forecast model. The simulation results demonstrate the proposed algorithm enhanced better forecasting accuracy.

Long-Term Load Forecasting of Southern Governorates of Jordan Distribution Electric System

Load forecasting is vitally important for electric industry in the deregulated economy. This paper aims to face the power crisis and to achieve energy security in Jordan. Our participation is localized in the southern parts of Jordan including, Ma’an, Karak and Aqaba. The available statistical data about the load of southern part of Jordan are supplied by electricity Distribution Company. Mathematical and statistical methods attempted to forecast future demand by determining trends of past results and use the trends to extrapolate the curve demand in the future.

Spatial and temporal synthesized probability gain for middle and long-term earthquake forecast and its preliminary application

The principle of middle and long-term earthquake forecast model of spatial and temporal synthesized probability gain and the evaluation of forecast efficiency (R-values) of various forecast methods are introduced in this paper. The R-value method, developed by Xu (1989), is further developed here, and can be applied to more complicated cases. Probability gains in spatial and/or temporal domains and the R-values for different forecast methods are estimated in North China. The synthesized probability gain is then estimated as an example.

Study of Holocene glacier degradation in central Asia by isotopic methods for long-term forecast of climate changes

This article presents a summary of our studies of Holocene moraines and glaciers of the Tien-Shan, Pamir, and Himalaya moun- mills with the purpose of providing pattern regularity of the Holocene glaciation decomposition. We developed a method for ob- taining reliable radiocarbon dating of moraines with the use of autochthonous organic matter dispersed in fine-grained morainic material, as well there were shown new possibilities of isotope-oxygen and isotope-uranium analysis for the Holocene glaciations dynamics. We found that Holocene glaciations disintegrate stadiaUy according to the decaying principle, and seven main stages may be distinguished. We achieved the absolute dating of the first three stages, identifying these periods as 8,000, 5,000, and 3,400 years ago. The application of the above-mentioned isotope methods of the Holocene glaciations and moraines study will allow re- searchers to improve the offered model of the Holocene glaciations disintegration; it will be great contribution to salvation of the problem of long-term climatic and glaciations forecast.

Long Term Load Forecasting and Recommendations for China Based on Support Vector Regression

Long-term load forecasting (LTLF) is a challenging task because of the complex relationships between load and factors affecting load. However, it is crucial for the economic growth of fast developing countries like China as the growth rate of gross domestic product (GDP) is expected to be 7.5%, according to China’s 11th Five-Year Plan (2006-2010). In this paper, LTLF with an economic factor, GDP, is implemented. A support vector regression (SVR) is applied as the training algorithm to obtain the nonlinear relationship between load and the economic factor GDP to improve the accuracy of forecasting.

Short-Term and Long-Term Price Forecasting Models for the Future Exchange of Mongolian Natural Sea Buckthorn Market

Sea buckthorn market floated uncertainly within a narrow range. The market situation provided upward pressure on prices, and producer and consumer interest were poor, coupled with weak prices in the regional markets. The objectives of the study are: 1) to estimate the relationship between wild Sea buckthorn (SB) price and Supply, Demand, while some other factors of crude oil price and exchange rate by using simultaneous Supply-Demand and Price system equation and Vector Error Correction Method (VECM);2) to forecast the short-term and long-term SB price;3) to compare and evaluate the price forecasting models. Firstly, the data was analyzed by Ferris and Engle-Granger’s procedure;secondly, both price forecasting methodologies were tested by Pindyck-Rubinfeld and Makridakis’s procedure. The result shows that the VECM model is more efficient using yearly data;a short-term price forecast decreases, and a long-term price forecast is predicted to increase the Mongolian Sea buckthorn market.

Stock Price Forecasting with Artificial Neural Networks Long Short-Term Memory: A Bibliometric Analysis and Systematic Literature Review

This study maps the academic literature on Stock Price Forecasting with Long-Term Memory Artificial Neural Networks—RNA LSTM. The objective is to know if it is suitable for time series studies, especially for stock price projection. Through bibliometric analysis and systematic literature review, it is observed that 333 authors wrote on the topic between 2018 and March 2022, and the journals Expert Systems with Applications, IEEE Access, Big Data Journal and Neural Computing and Applications, published the most relevant articles. Of the 99 articles published in this period, 43 are associated with Chinese institutions, the most cited being that of Kim and Won, who studies the volatility of returns and the market capitalization of South Korean stocks. The basis of 65% of the studies is the comparison between the RNN LSTM and other artificial neural networks. The daily closing price of shares is the most analyzed type of data, and the American (21%) and Chinese (20%) stock exchanges are the most studied. 57% of the studies include improvements to existing neural network models and 42% new projection models.

Long-term Energy Demand and CO_2 Problem in the PRC

The long-term energy demand in China and the-Chinese share in global CO2 emission are forecasted on the basis of scenarios of population growth and economy development up to 2050 proposed in view of the interaction of energy, economy, environment and social development. The total energy demand in 2050 will reach 4.4~ 5.4 billion tce. It is shown in energy supply analysis that coal is China’s major energy in primary energy supply. The share of CO2 emission in the future Chinese energy system will be out of proportion to its energy consumption share because of the high persentage of coal to be consumed. It will reach about 27%. The nuclear option which would replace 30.7% of coal in the total primary energy supply will reduce the share by 9.8%. So the policy considerations on the future Chinese energy system is of great importance to the global CO2 issues.

Long-term Prediction and Verification of Rainfall Based on the Seasonal Model

Using the seasonal cross-multiplication trend model, monthly precipitation of eight national basic weather stations of Shaanxi Province from 2005 to 2010 was predicted, and the forecast results were verified using the rainfall scoring rules of China Meteorological Administration. The verification results show that the average score of annual precipitation prediction in recent six years is higher than that made by a professional forecaster, so this model has a good prospect of application. Moreover, the level of making prediction is steady, and it can be widely used in long-term prediction of rainfall.

基于多模型融合的中长期径流集成预测方法

中长期水文预报是流域水资源规划与合理配置的重要依据。为提高中长期径流预测精度,提出了一种基于多模型融合的水库中长期径流集成预测方法。该方法将ARMA、BP、LSTM、RF和SVR等5个异质预测模型进行融合,同时采用超参数优化方法确定各模型的最优参数。将其用于青海省龙羊峡水库的中长期径流预报中,结果表明,通过Stacking融合算法建立的集成预测模型相较于单一模型,取得了更高的预测精度(R2值由0.71提升至0.82)。此方法可为提升流域中长期径流预测精度提供一定参考。

基于可解释机器学习的黄河源区径流分期组合预报

黄河源区是黄河流域重要的产流区和我国重要的清洁能源基地,提高黄河源区径流预报准确率可为流域水资源科学调配和水风光清洁能源高效利用提供重要支撑。以黄河源区唐乃亥和玛曲水文站为研究对象,基于不同月份径流组分的差异,考虑积雪覆盖率及融雪水当量变化,构建了中长期径流分期组合机器学习预报模型及其可解释性分析框架。研究结果表明:1)年内的径流预报时段可划分为融雪影响期(3—6月)和非融雪主导(以降雨和地下水补给为主)期(7月—次年2月);2)与传统不分期模型相比,唐乃亥站和玛曲站分期组合预报模型的纳什效率系数分别达0.897、0.835,确定系数(R2)分别达0.897、0.839,均方根误差分别降低了10%、17%,提高了径流预报准确率,通过分位数映射校正,唐乃亥站和玛曲站预报模型的R2分别进一步提升至0.926和0.850;3)基于SHAP机器学习可解释性分析框架,辨识了预报因子对径流预报结果的贡献程度,由高到低依次为降水、前一个月流量、蒸发、气温、相对湿度、融雪水当量等,发现了不同预报因子之间交互作用散点分布具有拖尾式或阶跃式的特征。

基于双重分解和双向长短时记忆网络的中长期负荷预测模型

针对中长期电力负荷序列噪声含量高、难以直接提取序列周期规律从而影响预测精度的问题,提出了一种基于完全自适应噪声集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)和奇异谱分析(singular spectrum analysis,SSA)双重分解的双向长短时记忆网络(bidirectional long and short time memory,BiLSTM)预测模型。首先,采用CEEMDAN对历史负荷进行分解,以得到若干个周期规律更为清晰的子序列;再利用多尺度熵(multiscale entropy,MSE)计算所有子序列的复杂程度,根据不同时间尺度上的样本熵值将相似的子序列重构聚合;然后,利用SSA去噪的功能,对高度复杂的新序列进行二次分解,去除序列中的噪声并提取更为主要的规律,从而进一步提高中长序列预测精度;再将得到的最终一组子序列输入BiLSTM进行预测;最后,考虑到天气、节假日等外部因素对电力负荷的影响,提出了一种误差修正技术。选取了巴拿马某地区的用电负荷进行实验,实验结果表明,经过双重分解可以将均方根误差降低87.4%;预测未来一年的负荷序列时,采用的BiLSTM模型将拟合系数最高提高2.5%;所提出的误差修正技术可将均方根误差降低9.7%。

基于集群辨识和卷积神经网络-双向长短期记忆-时序模式注意力机制的区域级短期负荷预测

为了解决区域级短期电力负荷预测时输入特征过多和负荷时序性较强的问题,提出一种基于集群辨识和卷积神经网络(convolutional neural networks,CNN)-双向长短期记忆网络(bi-directional long short-term memory,BiLSTM)-时序模式注意力机制(temporal pattern attention,TPA)的预测方法。首先,将用电模式和天气作为影响因素,基于二阶聚类算法对区域内的负荷节点进行集群辨识,再从每个集群中挑选代表特征作为深度学习模型的输入,这样既能减少输入特征维度,降低计算复杂度,又能综合考虑预测区域的整体特征,提升预测精度。然后,针对区域电力负荷时序性的特点,用CNN-BiLSTM-TPA模型完成训练和预测,该模型能提取输入数据的双向信息生成隐状态矩阵,并对隐状态矩阵的重要特征加权,从多时间步上捕获双向时序信息用于预测。最后,在美国加利福尼亚州实例上分析验证了所提方法的有效性。

胜利油田开发规划技术研究进展及展望

自20世纪90年代起,结合国际油价变化、勘探开发形势以及技术的进步,胜利油田形成一套与油田各开发阶段战略需求紧密契合的开发规划技术体系。立足胜利油田中长远开发规划编制实践,梳理了胜利油田开发规划技术的发展历程,介绍了各阶段开发规划技术发展的历史背景、技术思路以及面临问题。经过持续攻关和实践,胜利油田开发规划技术主要经历了方案优选、产量规划、效益规划、不确定性规划4个阶段,各阶段形成的开发规划技术有效支撑了开发规划方案的编制,指导了油田发展方向。围绕胜利油田可持续发展目标,明确了胜利油田现有开发规划技术存在新领域开发经济规律把握难度大、中长远规划与年度生产部署的结合需加强、规划编制的战略性及前瞻性需提升3方面的问题。针对存在问题,提出了下步胜利油田开发规划技术将向更注重不确定性及多目标、更加智能化、精细化以及更加具有战略性、前瞻性发展,为油田战略决策提供技术支撑。

基于聚类的HPO-BILSTM光伏功率短期预测

考虑到光伏发电功率在不同天气类型下的波动性和不确定性,对此提出一种基于模糊C均值聚类算法(FCM)和猎食者优化算法(HPO)优化双向长短期记忆网络(BILSTM)的光伏发电短期功率预测模型。首先对光伏发电数据进行处理和分析,再进行主成分分析(PCA)降维和FCM聚类算法将数据按天气类型分为阴、晴、雨;最后通过HPO筛选得出BILSTM神经网络的最佳超参数,避免因超参数设置不佳对实验带来的影响,进一步提高实验的准确性和模型的泛化能力。最后通过预测和对比实验进行分析,验证所提方法的优越性。

基于ISSA-LSTM模型的可再生能源电力需求预测

为了更精准地预测未来能源结构调整方向及成效,选用ISSA-LSTM组合预测模型对中国2023-2030年可再生能源的电力需求进行预测。首先,利用Circle混沌映射改进麻雀搜索算法(SSA)以提高搜索能力以及种群多样性;然后引入长短期记忆神经网络(LSTM)以有效捕捉可再生能源电力需求随机波动性和时序性;最后,通过ISSA-LSTM模型预测长期可再生能源的电力需求,验证测试集数据,并与其他传统模型进行对比。结果表明:ISSA-LSTM模型预测结果能够满足对可再生能源电力需求预测的精度要求;在未来2023-2030年可再生能源电力需求稳定,波动幅度不大,可达到全国用电量的1/3;利用Circle混沌映射改进策略能有效提升SSA寻优能力。与PSO算法相比,SSA算法寻找LSTM超参数最优解的能力更优,ISSA-LSTM模型预测可再生能源电力需求精度更高。

基于LSTM算法的冷轧机架振动动态预警分析

在实际生产阶段冷轧机具有多态性与时变性,需要对轧机振动动态预警进行转换形成包含多变量的时间序列预警。建立了一种基于LSTM算法的冷轧机振动预警模型。研究结果表明:提高步长后模型预警性能获得明显提升,随着步长到达5后,模型表现也逐渐变差,步长为4时,获得了最优预警效果。结合实际振动报警阈值,在预警振动能量值升高至阈值75%时激发形成振动预报,第一卷与第二卷分别提前预报1.6s与3.2s。该研究对控制板材的精度具有很好的指导意义。

基于VMD-FE-CNN-BiLSTM的短期光伏发电功率预测

为提高光伏功率的预测精度,提出一种变分模态分解(VMD)、模糊熵(FE)、卷积神经网络(CNN)和双向长短期记忆神经网络(BiLSTM)的光伏功率组合预测模型。该方法首先采用VMD将原始光伏序列数据分解成多个子序列,从而减少随机波动分量和噪声干扰对预测模型的影响,通过FE对每个子序列进行重组,使用一维CNN的局部连接及权值共享提取不同分量的特征,将CNN输出的特征融合并输入到BiLSTM模型中;利用BiLSTM模型建立历史数据之间的时间特征关系,得到光伏发电功率预测结果。与BiLSTM、CNN-BiLSTM、EEMD-CNN-BiLSTM、VMD-CNN-BiLSTM这4种模型进行比较,该文提出的VMD-FE-CNN-BiLSTM模型在光伏发电功率预测中具有较高的精确度和稳定性,满足光伏发电短期预测的要求。

基于改进Q学习算法和组合模型的超短期电力负荷预测

单一模型在进行超短期负荷预测时会因负荷波动而导致预测精度变差,针对此问题,提出一种基于深度学习算法的组合预测模型｡首先,采用变分模态分解对原始负荷序列进行分解,得到一系列的子序列。其次,分别采用双向长短期记忆网络和优化后的深度极限学习机对每个子序列进行预测。然后,利用改进Q学习算法对双向长短期记忆网络的预测结果和深度极限学习机的预测结果进行加权组合,得到每个子序列的预测结果。最后,将各个子序列的预测结果进行求和,得到最终的负荷预测结果。以某地真实负荷数据进行预测实验,结果表明所提预测模型较其他模型在超短期负荷预测中表现更佳,预测精度达到98%以上。

基于LSTM模型的船舶材料成本滚动预测

船舶建造周期长、材料成本占比大,易受大宗商品价格指数和汇率等多个因素的影响,造成实际完工成本与报价估算存在较大误差的情况。采用灰色关联分析(Grey Correlation Analysis,GCA)方法识别材料成本的影响因素,基于长短期记忆网络(Long Short-Term Memory,LSTM)模型构建船舶材料成本滚动预测模型,并使用某造船企业53艘64000 t散货船63个月的材料成本数据和对应的影响因素数据进行试验分析。结果表明,预测数据与实际数据误差在可接受范围内,可证明所选择方法和构建模型的有效性。研究结果对制造过程的成本实时预测和控制具有现实意义。