Short-term electricity price forecast based on the improved hybrid model

Half-hourly electricity price in power system are volatile, electricity price forecast is significant information which can help market managers and participants involved in electricity market to prepare their corresponding bidding strategies to maximize their benefits and utilities. However, the fluctuation of electricity price depends on the common effect of many factors and there is a very complicated random in its evolution process. Therefore, it is difficult to forecast half-hourly prices with traditional only one model for different behaviors of half-hourly prices. This paper proposes the improved forecasting model that detaches high volatility and daily seasonality for electricity price of New South Wales in Australia based on Empirical Mode Decomposition, Seasonal Adjustment and Autoregressive Integrated Moving Average. The prediction errors are analyzed and compared with the ones obtained from the traditional Seasonal Autoregressive Integrated Moving Average model. The comparisons demonstrate that the proposed model can improve the prediction accuracy noticeably.     

Performance evaluation of a wind driven DOIG using a hybrid model

This paper presents the performance analysis of a wind-driven double output induction generator (DOIG) operating at varying shaft speeds. A periodic transient state analysis of DOIG equipped with two controlled power converters is carried out using a hybrid induction machine model. It is shown that practical aspects of power converters such as overlap and harmonics reduce the power output of the DOIG system and limit the operating shaft speed range, especially in the subsynchronous region near the synchronous speed. The validity of the mathematical model used in the analyses and the corresponding computer simulation results are verified experimentally     

Forecasting electricity price and demand using a hybrid approach based on wavelet transform,ARIMA and neural networks

Demand and price forecasting are extremely important for participants in energy markets. Most research work in the area predicts demand and price signals separately. In this paper, a model is presented which predicts electricity demand and price simultaneously. The model combines wavelet transforms, ARIMA models and neural networks. Both time domain and wavelet domain variables are considered in the feature set for price and demand forecasting. The best input set is selected by two‐step correlation analysis. The proposed model is better adapted to real conditions of an energy market since the forecast features for price and demand are not assumed as known values but are predicted by the model, thus accounting for the interactions of the demand and price forecast processes. The forecast accuracy of the proposed method is evaluated using data from the Finnish energy market, which is part of the Nordic Power Pool. The results show that the proposed model provides significant improvement in both demand and price prediction accuracy compared with models using a separate frameworks approach. Copyright © 2013 John Wiley & Sons, Ltd.     

基于滑动窗口和LSTM神经网络的锂离子电池建模方法

为提高锂离子电池在复杂工况下的预测能力和建模精度,提出一种基于滑动窗口和长短时记忆(long short term memory,LSTM)神经网络的锂离子电池建模方法.首先建立了基于神经网络的锂离子电池模型,确定了神经网络的基本结构,通过LSTM层、向量拼接层和全连接层分别实现了时序特征提取、特征融合和回归预测.然后提出了滑动窗口的输入向量处理方法,滑动窗口每次向前推进一个时间点,通过限制时间窗口内所能处理的最大信元数对数据量进行限制,为多个LSTM层的并行计算和深隐层的拼接层和全连接层预留了计算量的裕度,实现了对模型中循环网络层深度的优化选择.为解决模型在多工况下运行的泛化问题,提出使用离线数据集的预训练和在线数据的参数修正的训练方法,通过大量离线数据集的反复训练,使模型学习电池的共性部分;再使用部分在线数据,对网络参数进行调整,将其应用于预测中.最后使用恒流/恒压、随机电流脉冲、大功率脉冲等多个工况的数据分别进行测试.结果表明,基于长短时记忆神经网络的建模方法能够准确预测电池输出电压和荷电状态.     

Oil price fluctuations and their impact on the macroeconomic variables of Kuwait: a case study using a VAR model

In this study, a vector autoregression model (VAR) and a vector error correction model (VECM) were estimated to examine the impact of oil price fluctuations on seven key macroeconomic variables for the Kuwaiti economy. Quarterly data for the period 1984–1998 were utilized. Theoretically and empirically speaking, VECM is superior to the VAR approach. Also, the results corresponding to the VECM model are closer to common sense. However, the estimated models indicate a high degree of interrelation between major macroeconomic variables. The empirical results highlight the causality running from the oil prices and oil revenues, to government development and current expenditure and then towards other variables. For the most part, the empirical evidence indicates that oil price shocks and hence oil revenues have a notable impact on government expenditure, both development and current. However, government development expenditure has been influenced relatively more. The results also point out the significance of the CPI in explaining a notable part of the variations of both types of government expenditure. On the other hand, the variations in value of imports are mostly accounted for by oil revenue fluctuations and then by the fluctuation in government development expenditures. Also, the results from the VECM approach indicate that a significant part of LM2 variance is explained by the variance in oil revenue. It reaches about 46 per cent in the 10th quarter, even more than its own variations. Copyright © 2001 John Wiley & Sons, Ltd.     

Prediction of hourly solar radiation using a novel hybrid model of ARMA and TDNN

In this work, a new approach that contains two phases is used to predict the hourly solar radiation series. In the detrending phase, several models are applied to remove the non-stationary trend lying in the solar radiation series. To judge the goodness of different detrending models, the Augmented Dickey-Fuller method is applied to test the stationarity of the residual. The optimal model is used to detrend the solar radiation series. In the prediction phase, the Autoregressive and Moving Average (ARMA) model is used to predict the stationary residual series. Furthermore, the controversial Time Delay Neural Network (TDNN) is applied to do the prediction. Because ARMA and TDNN have their own strength respectively, a novel hybrid model that combines both the ARMA and TDNN, is applied to produce better prediction. The simulation result shows that this hybrid model can take the advantages of both ARMA and TDNN and give excellent result.     

A novel hybrid model based on artificial neural networks for solar radiation prediction

As a kind of clean, substantial and renewable energy, solar energy can reduce environmental pollution with an extensive application potential. Precise prediction of global solar radiation has great significance for the design of solar energy systems and management of solar power plants.In this paper, a new hybrid model combining the SOM-OPELM with time series strategies is presented for predicting the global solar radiation on the horizon. In this model, the SOM divides the original data into distinct clusters and the OPELM establishes the prediction model. Subsequently, three population time series strategies, (i.e. Recursive strategy, DirRec strategy and MISMO strategy) are adopted to accomplish the multi-step prediction. A comparison between the proposed SOM-OPELM model and other conventional methods is carried out to demonstrate its efficiency and estimation performance. The simulation results show that the proposed SOM-OPELM model with DirRec strategy or MISMO strategy outperforms the following models: Recursive-BP, DirRec-BP, MISMO-BP, Recursive-SOM-OPELM and ARIMA.     

Value-at-risk estimation of crude oil price using MCA based transient risk modeling approach

With the increasing level of volatility in the crude oil market, the transient data feature becomes more prevalent in the market and is no longer ignorable during the risk measurement process. Since there are multiple representations for these transient data features using a set of bases available, the sparsity measure based Morphological Component Analysis (MCA) model is proposed in this paper to find the optimal combinations of representations to model these transient data features. Therefore, this paper proposes a MCA based hybrid methodology for analyzing and forecasting the risk evolution in the crude oil market. The underlying transient data components with distinct behaviors are extracted and analyzed using MCA model. The proposed algorithm incorporates these transient data features to adjust for conservative risk estimates from traditional approach based on normal market condition during its risk measurement process. The reliability and stability of Value at Risk (VaR) estimated improve as a result of finer modeling procedure in the multi frequency and time domain while maintaining competent accuracy level, as supported by empirical studies in the representative West Taxes Intermediate (WTI) and Brent crude oil market.     

Forecasting method of monthly wind power generation based on climate model and long short-term memory neural network

Predicting wind power generation over the medium and long term is helpful for dispatching departments, as it aids in constructing generation plans and electricity market transactions. This study presents a monthly wind power generation forecasting method based on a climate model and long short-term memory (LSTM) neural network. A nonlinear mapping model is established between the meteorological elements and wind power monthly utilization hours. After considering the meteorological data (as predicted for the future) and new installed capacity planning, the monthly wind power generation forecast results are output. A case study shows the effectiveness of the prediction method.     

Degradation prediction model for proton exchange membrane fuel cells based on long short-term memory neural network and Savitzky-Golay filter

Proton exchange membrane fuel cell (PEMFC) as a promising green power source, can be applied to vehicles, ships, and buildings. However, the lifetime of the fuel cell needs to be prolonged in order to achieve a wide range of applications. Consequently, the prediction of the health state draws attention lately and is critical to improving the reliability of the fuel cell. Since the degradation mechanism of the fuel cell is not fully understood, the data-driven method is very suitable for designing degradation prediction models. However, the data-driven method usually requires a lot of data, which is difficult to be obtained. To solve the issues, we propose a degradation prediction model for PEMFC based on long short-term memory neural network (LSTM) and Savitzky-Golay filter in this paper. First, we select the monitoring parameters for building the degradation prediction model by analyzing the degradation phenomenon of the fuel cell. Then, Savitzky-Golay filter is utilized to smooth out the selected data, and the sliding time window is used to generate training samples. Finally, the LSTM is applied to establish the degradation prediction model. Moreover, the dropout layer and mini-batch method are adopted to improve the model generalization ability. We use an actual aging data of the fuel cell to verified the proposed degradation prediction model. The results demonstrate that the proposed model can precisely predict the fuel cell degradation. It is worth mentioning that the determination coefficient (R²) of the test set based on the model trained by 25% of data is 0.9065.     

Quantitative risk assessment of a hydrogen refueling station by using a dynamic physical model based on multi-physics system-level modeling

Numerous accidents in HRSs have been reported worldwide in accident databases; therefore, many researchers have performed quantitative risk assessments (QRAs) of HRSs to enable risk-informed decision making in determining the safety distances or risk mitigation measures. The HRSs, located in urban areas such as Tokyo in Japan, are situated in congested areas with tall buildings and high population density; thus, they have relatively narrow station areas. However, the QRAs are generally suitable for large plants such as nuclear power plants or chemical plants; therefore, relatively small plants or installations, such as HRSs, have not yet been considered as QRA objects. Hence, it is necessary to conduct detailed QRAs with risk analyses and reduce the applied uncertainties for relatively small plants or installations. We applied a model-based approach of risk assessment to model the HRS process using multi-physics system-level modeling and simulated a target system using Modelica—an equation-based, object-oriented modeling language that allows acausal modeling of complex cyber-physical systems The primary aim of this study was to conduct a QRA of an HRS based on multi-physics system-level modeling. First, we modeled the HRS components and physical relationships between the components using basic physical equations. Then, we elucidate a QRA based on the constructed model. The difference in the leakage rates due to the leak positions and dynamic behavior of the model parameters were calculated using the constructed model. Finally, we estimated the individual risks of all the scenarios and compared the resulting risk contours based on the constructed model that includes the hydrogen-fuel dynamic behavior with those based on the traditional model. These results indicate that it is possible to assess whether the risks around the station boundary are acceptable based on the scenario information obtained by evaluating the risks near the station.     

Performance evaluation and optimization of a novel plug-in power-reflux hybrid electric vehicle powertrain

In order to improve the fuel economy of hybrid electric vehicles, a novel plug-in power-reflux hybrid electric vehicle powertrain equipped with an electromechanical control continuously variable transmission (EMCVT) is proposed in this study. The proposed structure, which combines the dynamic property of the planetary mechanism and regulating characteristics of the continuous speed ratio with EMCVT, can transmit power in two modes, namely power-reflux mode and pure-CVT mode, thus realizing the multistage design of the overall transmission system. Hence, it demonstrates a wider speed ratio variation range and higher transmission efficiency than the “Pathfinder-like” parallel configuration with traditional electro-hydraulic CVT (EHCVT). To take full advantage of its potential for fuel economy, the highest transmission efficiency of the system is taken as the optimization objective for the target speed ratio of the system. The optimization results are incorporated in the control strategy based on Pontryagin's minimum principle to simulate fuel consumption under the new European driving cycle (NEDC), highway fuel economy test (HWFET), and urban dynamometer driving schedule (UDDS). Compared with the simulation of the “THS II-like” configuration with similar vehicular parameters, the results show that the novel configuration has better fuel economy.     

Performance model of a novel evacuated-tube solar collector based on minichannels

Thermal performance of a novel minichannel-based solar collector is investigated numerically. The particular collector consists of a U-shaped flat-tube absorber with a selective coating on its external surface. The working fluid flows inside an array of minichannels located in the cross-section of the absorber along its length. The absorber is enclosed in an evacuated-glass envelope to minimize convective losses. Performance and pressure drop are evaluated for different inlet temperatures and flow rates of the working fluid. Thermal performance of minichannel-based solar collector is compared to that of an evacuated tube collector without minichannels from the literature. Configurations with and without a concentrator are analyzed.     

基于时变通信拓扑的可再生能源主动配电系统规划模型

在考虑信息通信系统和电力物理系统深度交互耦合的高比例可再生能源主动配电系统中,配电网优化规划决策不可避免地受到通信网络性能的影响。文章提出基于时变通信拓扑的可再生能源主动配电系统规划模型。首先基于电力信息物理深度融合系统和非理想时变通信拓扑特征在高比例可再生能源配电网规划中的作用机理,提出基于多智能体的主动配电系统规划架构;其次引入多智能体系统协同控制方法,研究具有通信时延和攻击行为节点的复杂网络环境下通信时延多智能体系统,提出具有自适应能力的一致性控制方法;最后通过仿真算例验证了所提方法对于具有通信时延和遭遇恶意节点攻击下可再生能源主动配电系统规划安全一致的有效性,并通过电压偏移灵敏度测试,验证了信息传输质量对于物理系统的影响。考虑多智能体主动配电系统物理系统和信息系统的协同规划,有利于配电网安全、可靠、稳定运行,能够为主动配电系统优化规划提供决策依据。     

Power entity recognition based on bidirectional long short-term memory and conditional random fields

With the application of artificial intelligence technology in the power industry, the knowledge graph is expected to play a key role in power grid dispatch processes, intelligent maintenance, and customer service response provision. Knowledge graphs are usually constructed based on entity recognition. Specifically, based on the mining of entity attributes and relationships, domain knowledge graphs can be constructed through knowledge fusion. In this work, the entities and characteristics of power entity recognition are analyzed, the mechanism of entity recognition is clarified, and entity recognition techniques are analyzed in the context of the power domain. Power entity recognition based on the conditional random fields (CRF) and bidirectional long short-term memory (BLSTM) models is investigated, and the two methods are comparatively analyzed. The results indicated that the CRF model, with an accuracy of 83%, can better identify the power entities compared to the BLSTM. The CRF approach can thus be applied to the entity extraction for knowledge graph construction in the power field.     

Degradation prediction of proton exchange membrane fuel cell using auto-encoder based health indicator and long short-term memory network

As durability of proton exchange membrane fuel cell (PEMFC) remains as the main obstacle for its larger scale commercialization, predicting PEMFC degradation progress is thus an effective way to extend its lifetime. To realize reliable prediction, a novel health indicator (HI) extraction method based on auto-encoder is proposed in this paper, with which PEMFC future voltage can be predicted by long short-term memory network (LSTM). The effectiveness and robustness of proposed approach is investigated with test data simulating vehicle operation conditions, and accurate prediction performance can be observed, with the maximum root mean square error (RMSE) of 0.003513. Moreover, by comparing with two commonly prognostic methods including attention-based gated recurrent unit network and polarization model-LSTM, the proposed method can provide better predictions under various operating conditions. Furthermore, with the proposed method, the degradation mechanism of PEMFC can also be analyzed. Therefore, the proposed prognostic method can predict reliable PEMFC degradation progress and its corresponding degradation mechanisms, which will be beneficial in practical PEMFC systems for taking appropriate strategies to guarantee PEMFC durability.     

Remaining useful life prediction of PEMFC based on long short-term memory recurrent neural networks

To solve the prediction problem of proton exchange membrane fuel cell (PEMFC) remaining useful life (RUL), a novel RUL prediction approach of PEMFC based on long short-term memory (LSTM) recurrent neural networks (RNN) has been developed. The method uses regular interval sampling and locally weighted scatterplot smoothing (LOESS) to realize data reconstruction and data smoothing. Not only the primary trend of the original data can be preserved, but noise and spikes can be effectively removed. The LSTM RNN is adopted to estimate the remaining life of test data. 1154-hour experimental aging analysis of PEMFC shows that the prediction accuracy of the novel method is 99.23%, the root mean square error (RMSE) and mean absolute error (MAE) is 0.003 and 0.0026 respectively. The comparison analysis shows that the prediction accuracy of the novel method is 28.46% higher than that of back propagation neural network (BPNN). Root mean square error, relative error (RE) and mean absolute error are all much smaller than that of BPNN. Therefore, the novel method can quickly and accurately forecast the residual service life of the fuel cell.     

Wind speed forecast model for wind farm based on a hybrid machine learning algorithm

This paper presents a new strategy for wind speed forecasting based on a hybrid machine learning algorithm, composed of a data filtering technique based on wavelet transform (WT) and a soft computing model based on the fuzzy ARTMAP (FA) network. The prediction capability of the proposed hybrid WT+FA model is demonstrated by an extensive comparison with some other existing wind speed forecasting methods. The results show a significant improvement in forecasting error through the application of a proposed hybrid WT+FA model. The proposed wind speed forecasting strategy is applied to real data acquired from the North Cape wind farm located in PEI, Canada.     

A novel algorithm for prediction of crude oil price variation based on soft computing

In this paper a method based on soft computing approaches is developed to predict the daily variation of the crude oil price of the West Texas Intermediate (WTI). The predicted daily oil price variation is compared with the actual daily variation of the oil price and the difference is implemented to activate the learning algorithms. In order to reduce the effect of unpredictable short term disturbances, a data filtering algorithm is used. In this paper, the prediction is called “true” if the predicted variation of the oil price has the same sign as the actual variation, otherwise the prediction is “false”. It is shown that for several randomly selected durations, the true prediction is considerably higher than the result of most recent published prediction algorithms. To ensure the accuracy and reliability of the algorithm, several on line predictions are executed during one complete month. The on line results indicate that the true predictions are consistently the same percentage for periods of one month.