Novel Hybrid Physics‑Informed Deep Neural Network for Dynamic Load Prediction of Electric Cable Shovel

Electric cable shovel(ECS)is a complex production equipment,which is widely utilized in open-pit mines.Rational valuations of load is the foundation for the development of intelligent or unmanned ECS,since it directly influences the planning of digging trajectories and energy consumption.Load prediction of ECS mainly consists of two types of methods:physics-based modeling and data-driven methods.The former approach is based on known physical laws,usually,it is necessarily approximations of reality due to incomplete knowledge of certain processes,which introduces bias.The latter captures features/patterns from data in an end-to-end manner without dwelling on domain expertise but requires a large amount of accurately labeled data to achieve generalization,which introduces variance.In addition,some parts of load are non-observable and latent,which cannot be measured from actual system sensing,so they can’t be predicted by data-driven methods.Herein,an innovative hybrid physics-informed deep neural network(HPINN)architecture,which combines physics-based models and data-driven methods to predict dynamic load of ECS,is presented.In the proposed framework,some parts of the theoretical model are incorporated,while capturing the difficult-to-model part by training a highly expressive approximator with data.Prior physics knowledge,such as Lagrangian mechanics and the conservation of energy,is considered extra constraints,and embedded in the overall loss function to enforce model training in a feasible solution space.The satisfactory performance of the proposed framework is verified through both synthetic and actual measurement dataset.

A comprehensive review for wind,solar,and electrical load forecasting methods

Wind power,solar power,and electrical load forecasting are essential works to ensure the safe and stable operation of the electric power system.With the increasing permeability of new energy and the rising demand response load,the uncertainty on the production and load sides are both increased,bringing new challenges to the forecasting work and putting forward higher requirements to the forecasting accuracy.Most review/survey papers focus on one specific forecasting object(wind,solar,or load),a few involve the above two or three objects,but the forecasting objects are surveyed separately.Some papers predict at least two kinds of objects simultaneously to cope with the increasing uncertainty at both production and load sides.However,there is no corresponding review at present.Hence,our study provides a comprehensive review of wind,solar,and electrical load forecasting methods.Furthermore,the survey of Numerical Weather Prediction wind speed/irradiance correction methods is also included in this manuscript.Challenges and future research directions are discussed at last.

Deep learning for time series forecasting:The electric load case

Management and efficient operations in critical infrastructures such as smart grids take huge advantage of accurate power load forecasting,which,due to its non-linear nature,remains a challenging task.Recently,deep learning has emerged in the machine learning field achieving impressive performance in a vast range of tasks,from image classification to machine translation.Applications of deep learning models to the electric load forecasting problem are gaining interest among researchers as well as the industry,but a comprehensive and sound comparison among different-also traditional-architectures is not yet available in the literature.This work aims at filling the gap by reviewing and experimentally evaluating four real world datasets on the most recent trends in electric load forecasting,by contrasting deep learning architectures on short-term forecast(oneday-ahead prediction).Specifically,the focus is on feedforward and recurrent neural networks,sequence-to-sequence models and temporal convolutional neural networks along with architectural variants,which are known in the signal processing community but are novel to the load forecasting one.

Short-Term Electricity Price Forecasting Using a Combination of Neural Networks and Fuzzy Inference

This paper presents an artificial neural network, ANN, based approach for estimating short-term wholesale electricity prices using past price and demand data. The objective is to utilize the piecewise continuous na-ture of electricity prices on the time domain by clustering the input data into time ranges where the variation trends are maintained. Due to the imprecise nature of cluster boundaries a fuzzy inference technique is em-ployed to handle data that lies at the intersections. As a necessary step in forecasting prices the anticipated electricity demand at the target time is estimated first using a separate ANN. The Australian New-South Wales electricity market data was used to test the system. The developed system shows considerable im-provement in performance compared with approaches that regard price data as a single continuous time se-ries, achieving MAPE of less than 2% for hours with steady prices and 8% for the clusters covering time pe-riods with price spikes.

Distributed Model Predictive Load Frequency Control of Multi-area Power System with DFIGs

Reliable load frequency control(LFC) is crucial to the operation and design of modern electric power systems. Considering the LFC problem of a four-area interconnected power system with wind turbines, this paper presents a distributed model predictive control(DMPC) based on coordination scheme.The proposed algorithm solves a series of local optimization problems to minimize a performance objective for each control area. The generation rate constraints(GRCs), load disturbance changes, and the wind speed constraints are considered. Furthermore, the DMPC algorithm may reduce the impact of the randomness and intermittence of wind turbine effectively. A performance comparison between the proposed controller with and without the participation of the wind turbines is carried out. Analysis and simulation results show possible improvements on closed–loop performance, and computational burden with the physical constraints.

Study on Relationship between Summer Electricity and Meteorology in Changsha City

[ Objective] The research aimed to study relationship between summer electricity and meteorological factors. [ Method] Electrical load characteristics in Changsha during 2007 -2010 were analyzed. Correlation analysis between electrical load and meteorological factors （daily average temperature, the maximum temperature, the minimum temperature, rainfall, wind, relative humidity and atmospheric pressure） during July - September of 2007 -2010 was conducted. [ Result] Changes of the meteorological factors could directly affect electrical load, and temperature was the first influence factor. Prediction model of summer electrical load in Changsha was established by regression analysis method.[ Conclusion] The research could provide reference basis for prediction of the electrical load in Changsha.

Data-Driven Load Forecasting Using Machine Learning and Meteorological Data

Electrical load forecasting is very crucial for electrical power systems’planning and operation.Both electrical buildings’load demand and meteorological datasets may contain hidden patterns that are required to be investigated and studied to show their potential impact on load forecasting.The meteorological data are analyzed in this study through different data mining techniques aiming to predict the electrical load demand of a factory located in Riyadh,Saudi Arabia.The factory load and meteorological data used in this study are recorded hourly between 2016 and 2017.These data are provided by King Abdullah City for Atomic and Renewable Energy and Saudi Electricity Company at a site located in Riyadh.After applying the data pre-processing techniques to prepare the data,different machine learning algorithms,namely Artificial Neural Network and Support Vector Regression(SVR),are applied and compared to predict the factory load.In addition,for the sake of selecting the optimal set of features,13 different combinations of features are investigated in this study.The outcomes of this study emphasize selecting the optimal set of features as more features may add complexity to the learning process.Finally,the SVR algorithm with six features provides the most accurate prediction values to predict the factory load.

基于动态自适应图神经网络的电动汽车充电负荷预测

电动汽车充电站负荷波动的不确定性与长时间预测任务给提升充电负荷预测精度带来巨大的挑战。文中提出一种基于动态自适应图神经网络的电动汽车充电负荷预测算法。首先,构建了一个充电负荷信息时空关联特征提取层,将多头注意力机制与自适应相关图结合生成具有时空关联性的综合特征表达式,以捕获充电站负荷的波动性;然后,将提取的特征输入到时空卷积层,捕获时间和空间之间的耦合关系;最后,通过切比雪夫多项式图卷积与多尺度时间卷积提升模型耦合长时间序列之间的能力。以Palo Alto数据集为例,与现有方法相比,所提算法在4种波动情况下的平均预测误差大幅降低。

基于可进化模型预测控制的含电动汽车多微电网智能发电控制策略

多微电网中的环境状态、控制资源及偶然事件均具有强不确定性,而电动汽车在参与电网削峰填谷的同时也给发电控制带来了挑战。为此,该文提出一种基于可进化模型预测控制(LBMPC)的含电动汽车多微电网发电控制策略。首先,基于控制器交互的多微电网互联结构,考虑了发电机端电压调节和负荷频率控制(LFC)之间的耦合关系,建立含电动汽车多微电网的发电控制模型;然后,设计了一种基于多智能体的控制器参数自适应算法:频率控制器以实时频偏和EV站输出功率边界为状态集,以模型预测控制(MPC)控制器的可调参数矩阵Q_(x)作为动作集,以频率偏差为奖励函数指标,电压控制器同理,从而实现MPC与PI控制器权重参数的自适应调整;最后,仿真结果表明,自动调压(AVR)回路增加了有功功率干扰,对LFC控制器提出了更高的要求,与传统控制和MPC算法相比,应用于控制器互联结构的可进化模型预测控制器能够在子微电网之间进行信息交换,并且根据环境状态实时更新控制器参数,显著提高了多微电网频率控制过程的鲁棒性和快速性。同时,与纯深度确定性策略梯度(DDPG)控制器相比,该文提出的双层控制结构在机器学习智能体出现故障无法正常输出动作时,能更好地保证系统的安全稳定运行。

基于改进LSTM神经网络的电动汽车充电负荷预测

当前对电动汽车(EV)充电负荷预测的研究缺少真实的数据支撑,并且模型考虑场景过于简单,影响因素考虑不到位,预测结果缺乏说服力。基于此,提出一种考虑多种电动汽车充电负荷影响因素的电动汽车充电负荷预测方法。首先,考虑天气、季节、温度、工作日、节假日等因素对电动汽车充电负荷的影响,采用三标度层次分析法分析各影响因素权重;其次,建立LSTM神经网络预测模型,通过真实数据训练得到用于预测的LSTM神经网络模型,结合影响因素权重分析结果对预测模型进行修正,得到最终的改进LSTM神经网络负荷预测模型;最后,采用常州某小区的真实数据对所提预测方法进行试验验证。结果表明,所提方法可以实现电动汽车充电负荷的精确预测,且负荷预测结果可为有序充电策略研究提供参考。

计及电动汽车保有量增长需求的充电负荷预测

当前对电动汽车充电负荷的研究大多集中在短期演变,对长时间尺度下的发展情况并未有较多研究。文中提出一种电动汽车保有量增长需求的充电负荷预测模型。首先采用萤火虫算法优化电动汽车保有量灰色预测模型的相关参数,对某地区2023—2033年电动汽车保有量进行预测;其次,综合考虑保有量预测结果、用户出行链、行驶里程及充电起始时间,结合在不同温度下的电动汽车电池容量和充电效率搭建充电负荷预测模型;最后,对江苏省某地区2023—2033年电动汽车充电负荷进行仿真预测。仿真结果有效地预测了电动汽车在未来10年中保有量发展趋势以及考虑保有量增长需求的充电负荷。

基于蒙特卡洛算法的大规模电动汽车充电负荷预测

电动汽车充电负荷的有效预测对配电网的安全稳定运行有重大意义。以某地区不同类型电动汽车的保有量预测结果为基础,将用户出行习惯、电动汽车的充电功率、充电时长等因素作为模型参数,利用蒙特卡洛模拟算法建立了考虑电动汽车类型的充电负荷预测模型,对该地区电动汽车的充电负荷进行预测。结果表明,未来电动汽车充电负荷增长较快,2025年较2022年充电负荷增长近70%,且不同类型充电负荷有不同的特征。该方法能提升电网负荷预测精确度,为配电网的调度与规划提供技术支撑。

基于供需两侧协同优化的电动汽车V2G充放电负荷时空分布预测研究

为准确预测电动汽车的V2G充放电负荷,以调节电网负荷峰谷差,保证供电稳定性,提出了一种基于供需两侧协同优化的电动汽车V2G充放电负荷时空分布预测方法。构建供需两侧协同优化目标模型,利用鲸鱼优化算法迭代求解,得出最优充放电负荷曲线,据此明确最优充放电时段。采集不同空间区域最优充放电时段内的充放电负荷影响指标,并以此为输入,构建基于多元线性回归的预测模型,实现电动汽车V2G充放电负荷时空分布预测。试验结果表明,采用所提出的方法得到的负荷预测模型具有较大的决定系数,表明该方法的预测结果更接近实际负荷,具有较高的预测准确性。

基于多维关联规则的用电负荷智能预测方法

用电负荷预测受到冗余数据影响,负荷预测值与实际值相差较大,因此提出基于多维关联规则的用电负荷智能预测方法。使用多维关联规则挖掘用电负荷频繁项集,获取全部用电负荷待预测数据,根据挖掘结果划分用电负荷种类。计算多维关联规则提升度,预处理冗余数据,生成待预测目标集。根据获取的用电序列,整合全部频繁项集,构建预测模型,并进行强关联学习。通过调整负荷数据训练收敛程度,获取用电负荷的最大、最小值。在用电设备节点中注入用电负荷预测多维关联规则修正数值,避免噪声数据影响预测结果。实验结果表明,该方法最大、最小负荷与实际数据,分别在9月30日和6月15日存在5 MW和0.3 MW的误差,说明该方法预测结果精准。

飞机舵机电动加载系统的非线性干扰抑制方法

飞机舵机电动加载系统是一个复杂的非线性机电控制系统,在运行过程中会产生多余力矩、摩擦、机械间隙等非线性干扰;针对以上问题,介绍了系统的硬件结构和工作原理,建立了系统的数学模型;在此基础上分析了非线性干扰的产生机理和工作特性,并根据加载系统领域非线性干扰抑制方法的研究,从结构与控制的两个方面进行归纳分类,进行性能对比以及适用性分析;针对多余力矩抑制的问题,提出了模型预测控制方案对其进行补偿,实验结果表明可以较准确地跟踪指令力矩,误差率小于1.93%,多余力矩的消除率达到95.86%;证明了所提出的方案的有效性,能够改善多余力矩的抑制能力,提高系统跟踪精度。

“双碳”“双区”背景下电力需求预测方法研究实践

为全面、准确分析新时期发展背景下城市未来用电特征,要结合新形势、新特点,考虑多种新要素,在以往所用方式、方法的基础上进行优化、调整,建立适合“双碳”“双区”发展目标的电力需求预测新体系。该文首先对“双碳”“双区”对城市电力需求预测影响进行分析,并提出碳强度约束下电能占终端能源比重法、细分产业法和新型负荷修正法3种电力需求预测方法,综合预测分析全社会用电量,了解城市中长期电力需求的具体特征,掌握用电总量趋势、用电结构趋势和最高负荷及负荷特性趋势,为城市发展规划顶层设计、控制电力负荷和提高电力投资效益提供参考。

售电公司电力现货交易辅助决策系统关键技术研究

对电价预测关键技术、用户负荷预测关键技术和零售套餐设计与测算关键技术进行研究。结合基于XGBDT的电价预测算法与基于人工神经网络的电价预测算法,提出了启发式组合电价预测算法,该算法计算简便、预测准确并且能够进行人工调节。将支持向量回归法用于用户负荷预测,用户负荷预测的精度和效率都较高。建立售电公司电力现货交易辅助决策系统,其功能包括市场分析、出清电价预测、用户负荷预测、现货交易决策、中长期交易管理、零售交易管理等,有助于售电公司降低交易风险,增加现货交易收益。

基于DBO-VMD和IWOA-BILSTM神经网络组合模型的短期电力负荷预测

新能源在现代电力系统中占比不断提高,其负荷不规律性、波动性远大于传统电力系统,这就导致负荷预测精度不高。针对这个问题,提出了蜣螂优化(dung beetle optimizer,DBO)算法优化变分模态分解(variational mode decomposition,VMD)与改进鲸鱼优化算法优化双向长短期记忆(improved whale optimization algorithm-bidirectional long short-term memory,IWOA-BILSTM)神经网络相结合的短期负荷预测模型。首先利用DBO优化VMD,分解时间序列数据,并根据最小包络熵对各种特征数据进行分类,增强了分解效果。通过对原始数据进行有效分解,降低了数据的波动性。然后使用非线性收敛因子、自适应权重策略与随机差分法变异策略增强鲸鱼优化算法的局部及全局搜索能力得到改进鲸鱼优化算法(improved whale optimization algorithm,IWOA),并用于优化双向长短期记忆(bidirectional long short-term memory,BILSTM)神经网络,增加了模型预测的精确度。最后将所提方法应用于某地真实的负荷数据,得到最终相对均方根误差、平均绝对误差和平均绝对百分比误差分别为0.0084、48.09、0.66%,证明了提出的模型对于短期负荷预测的有效性。

A Power Load Prediction by LSTM Model Based on the Double Attention Mechanism for Hospital Building

This work proposed a LSTM(long short-term memory)model based on the double attention mechanism for power load prediction,to further improve the energy-saving potential and accurately control the distribution of power load into each department of the hospital.Firstly,the key influencing factors of the power loads were screened based on the grey relational degree analysis.Secondly,in view of the characteristics of the power loads affected by various factors and time series changes,the feature attention mechanism and sequential attention mechanism were introduced on the basis of LSTM network.The former was used to analyze the relationship between the historical information and input variables autonomously to extract important features,and the latter was used to select the historical information at critical moments of LSTM network to improve the stability of long-term prediction effects.In the end,the experimental results from the power loads of Shanxi Eye Hospital show that the LSTM model based on the double attention mechanism has the higher forecasting accuracy and stability than the conventional LSTM,CNN-LSTM and attention-LSTM models.

基于长短期记忆神经网络的电力用电量预测

为解决现有用电量预测精确度较低等问题,提出了基于长短期记忆神经网络的电力用电量预测方法。分析了电力负荷分类以及典型负荷曲线,说明了支持向量回归以及长短期记忆神经网络的基本原理,提出了基于支持向量回归和长短期记忆神经网络结合的预测方法,说明了预测流程,给出了预测结果统计评价标准。根据所提出的方法进行了案例分析,论证了所提方法的有效性。