Accurate Forecasting Results Research Articles

Water quality forecasting based on data decomposition, fuzzy clustering and deep learning neural network

Water quality forecasting can provide useful information for public health protection and support water resources management. In order to forecast water quality more accurately, this paper proposes a novel hybrid model by combining data decomposition, fuzzy C-means clustering and bidirectional gated recurrent unit. Firstly, the original water quality data is decomposed into several subseries by empirical wavelet transform, and then, the decomposed subseries are recombined by fuzzy C-means clustering. Next, for each clustered series, bidirectional gated recurrent unit is applied to develop prediction model. Finally, the forecast result is obtained by the summation of the predictions for the subseries. The proposed forecast model is evaluated by the water quality data of Poyang Lake, China. Results show that the proposed forecast model provides highly accurate forecast result for all of the six water quality data: the average of MAPE of the forecast results for the six water quality datasets is 4.59% for 7 day ahead prediction. Furthermore, our model shows better forecast performance than the other models. Particularly, compared with the single BiGRU model, MAPE decreased by 32.86% in average. Results demonstrate that the proposed forecast model can be used effectively for water quality forecasting.

Short-term forecasting for multiple wind farms based on transformer model

With the rapid growth of wind power installed capacity in recent years, the distribution of wind farms will be relatively dense, and there are usually multiple wind farms in the same area. However, due to the complex correlations and dependencies among these wind farms, traditional forecasting models for individual wind power are difficult to apply. Meanwhile, the accurate forecasting of power output of multiple wind farms is very important to the evaluation results of the renewable energy consumption capacity of the grid, and this problem has received extensive attention from many scholars. To improve the accuracy of forecasting, we apply the Transformer model from natural language processing (NLP) to the field of wind power forecasting. The proposed model is capable of capturing longer sequence internal dependencies, as well as capturing the key information of wind data in a comprehensive and multifaceted way. By comparing with the comparison method, case studies show that the model is not only able to accurately extract different levels of correlation between multiple wind farms, but also to give accurate wind power forecasting results.

Transfer learning based multi-layer extreme learning machine for probabilistic wind power forecasting

With the increasing penetration of wind power, probabilistic forecasting becomes critical to quantifying wind power uncertainties and guiding power system operations. This paper proposes a transfer learning based probabilistic wind power forecasting method. Model-based transfer learning is utilized to construct the multi-layer extreme learning machine (MLELM). The output mapping factors of MLELM are further optimized through the particle swarm optimization (PSO) with the objective of minimizing the quantile evaluation indexes. Joint distribution adaptation (JDA) is utilized to update the weights of MLELM to accommodate variable wind power output. Test results on the practical wind farms in China shows that the proposed method can provide more accurate quantile forecasting results with better nonlinear fitting ability compared with other quantile forecasting methods.

Advanced traffic congestion early warning system based on traffic flow forecasting and extenics evaluation

Traffic congestion is a vital factor hindering travel. As such, developing a reliable traffic congestion early warning system is essential for providing traffic condition supervision and programming. However, previous research has rarely focused on traffic flow characteristics or on providing comprehensive assessments, resulting in poor warning performances. In this study, an innovative traffic congestion early warning system is proposed, comprising point forecasting, characteristic estimate, interval prediction, and comprehensive assessment. In the characteristic assessment phase, eight common statistical distributions are used to fit the characteristics of an original traffic flow parameter series in a training set, and the best fitting results are considered as the basis for building a prediction interval. An extreme learning machine combined with a modified multi-objective dragonfly optimization algorithm and variational mode decomposition is constructed in the point forecasting phase to provide accurate and stable traffic flow parameter forecasting results; two different strategies are used to establish the prediction interval, so as to conduct interval forecasting based on different types of uncertainty information (probability distribution information or known interval information). Extenics evaluation theory is then used in the comprehensive assessment phase to evaluate the traffic congestion level. Simulations of traffic flow parameter series, including simulations of the road density, road occupancy, and average velocity, reveal that the proposed early warning system demonstrates powerful abilities based on its precision and stability. The mean absolute percentage error (MAPE) values of the traffic flow parameters for the three datasets are 3.6265%, 3.7203%, and 4.5100%, respectively. The forecasting accuracy for the traffic congestion level is more than 97% for both point and interval prediction. Thus, this approach can be widely used for personal traffic route planning and the unified management of governmental traffic conditions.

Optimization of Raw Material Inventory Control CV. Dirga Eggtray Pinrang Using Probabilistic Model with Backorder and Lostsales Condition

This research discusses about the comparison of raw material inventory control CV. Dirga Eggtray Pinrang. It starts with forecasting inventory for the next 12 periods using variations of the time series forecasting method, where the linear regression method provides accurate forecasting results with a Mean Absolute Percentage Error (MAPE) value of 1,9371%. The probabilistic models of inventory control used are the simple probabilistic model, Continuous Review System (CRS) model, and Periodic Review System (PRS) model. The CRS model with backorder condition is a model that provides the minimum cost of Rp. 969.273.706,20 per year compared to another probabilistic model with the largest difference of Rp. 1.291.814,95 per year, with the optimum number of order kg, reorder level kg, and safety stock kg.

Optimal Dispatch of WT/PV/ES Combined Generation System Based on Cyber-Physical-Social Integration

With the energy transition, the cyber-physical system (CPS) is expanded to the cyber-physical-social system (CPSS), and connected by the communication network, which is introduced in the form of a highly reliable cellular star network in this paper. Due to the uncertainties of wind turbine/photovoltaic power outputs, an improved rolling ultra-short-term forecast method with high reliability is proposed, which is based on long short-term memory networks, and the superiority is proved by comparing with multi-layer perception neural networks, linear regression, support vector regression and random forest. Then, two stochastic optimization models are constructed, one is based on CPS, the other is based on CPSS. As for social factors, electric vehicle aggregator is stimulated by cost to actively participate in the dispatch operation. Moreover, in order to ensure the stable operation of the smart energy system, the frequency deviation of automatic generation control system is studied as one security constraint. The optimal results display that social factors can not only make the system more economic and flexible, but also further increase the consumption of RE. Moreover, accurate forecast results can improve the performance of optimization dispatch operations.

Short-Term Load Forecasting Method Based on Feature Preference Strategy and LightGBM-XGboost

Short term load forecasting is one of the important problems in power system. Accurate forecasting results can improve the flexibility of power market and resource utilization efficiency, which is of great significance to the efficient operation of power system.A short-term power load forecasting model based on feature selection and error correction is proposed to address the problems of low accuracy and weak generalization ability of short-term power load forecasting. The coarse set of features is firstly screened by using Maximal Information Coefficient (MIC), and then the fine set of key features affecting load forecasting is screened by using LightGBM and XGboost feature selection algorithms respectively. The corresponding fine set of features and historical loads are input into LightGBM and XGboost models with powerful prediction function for prediction, and use the predicted value to correct the error and complete the load prediction. Taking the actual data of a certain area in Northwest China as an example, the experimental results show that the proposed model has better prediction effect than other models.

Performance analysis of artificial neural network models for hour-ahead electric load forecasting

Supervised Artificial Neural Networks (ANN) is considered as a popular machine learning framework for year-ahead, month-ahead and day-ahead electric load forecasting but is yet to be optimized for very short term predictions like hour-ahead forecasting granularity. This study conducted a performance analysis of ANN models for hour-ahead electric load forecasting that power utility companies can use for agile reaction to its participation among spot markets. Data preparation procedures were conducted which transformed the historical electric load records of a certain geographic area served by a power utility into appropriate forms resulting to partitioned, represented and normalized datasets for ANN training and testing processes. Thirty-six ANN models all having nine input neurons and one output neuron were evaluated and found out that ANN models with Sigmoid activation function exhibited promising forecasting performance shown in terms of Mean Absolute Percentage Error (MAPE) with Back Propagation training algorithm with three hidden neurons having 2.85% MAPE; Quick Propagation training algorithm with six hidden neurons having 2.91% MAPE; and Resilient Propagation training algorithm with six hidden neurons having 3.49% MAPE. The performance analysis presented in this study shows how these ANN models were able to generate close to accurate forecasting results which power utility companies can effectively use for optimal resource management as they participate in spot markets that will require internationally accepted forecasting tolerance error in hour-ahead electric load nomination.

Ensemble Forecasting Frame Based on Deep Learning and Multi-Objective Optimization for Planning Solar Energy Management: A Case Study

There are many prediction models that have been adopted to predict uncertain and non-linear photovoltaic power time series. Nonetheless, most models neglected the validity of data preprocessing and ensemble learning strategies, which leads to low forecasting precision and low stability of photovoltaic power. To effectively enhance photovoltaic power forecasting accuracy and stability, an ensemble forecasting frame based on the data pretreatment technology, multi-objective optimization algorithm, statistical method, and deep learning methods is developed. The proposed forecasting frame successfully integrates the advantages of multiple algorithms and validly depict the linear and nonlinear characteristic of photovoltaic power time series, which is conductive to achieving accurate and stable photovoltaic power forecasting results. Three datasets of 15-min photovoltaic power output data obtained from different time periods in Belgium were employed to verify the validity of the proposed system. The simulation results prove that the proposed forecasting frame positively surpasses all comparative hybrid models, ensemble models, and classical models in terms of prediction accuracy and stabilization. For one-, two-, and three-step predictions, the MAPE values obtained from the proposed frame were less than 2, 3, and 5%, respectively. Discussion results also verify that the proposed forecasting frame is obviously different from other comparative models, and is more stable and high-efficiency. Thus, the proposed frame is highly serviceable in elevating photovoltaic power forecasting performance and can be used as an efficient instrument for intelligent grid programming.

Multivariate Air Quality Forecasting With Nested Long Short Term Memory Neural Network

Artificial intelligence-based air quality index (AQI) forecasting is a hot research topic in the fields of sustainable and smart industrial environment design. There are mainly two obstacles that hinder the existing machine learning (ML) and deep learning (DL) technologies providing accurate forecasting results to protect the environment, which include the intercorrelation between different AQI components and the highly volatile AQI pattern changes. In this article, a novel DL framework combining multiple nested long short term memory networks (MTMC-NLSTM) is proposed for accurate AQI forecasting enlightened with the federated learning. The performance of the proposed MTMC-NLSTM model is compared with conventional ML models, DL methods, as well as hybrid DL models. The experimental results show that the performance of the proposed method is superior to those of all compared models.

Two types of conformable fractional grey interval models and their applications in regional electricity consumption prediction

Taking the unbalance development inside a region into consideration, it will be better to express the regional electricity consumption (EC) value as an interval number to preserve more complete information. However, there are rare papers about this interesting topic. For the small amount of EC data, grey interval prediction model is employed in this paper. However, the existing models are almost all integer-order grey interval models and based on area coordinate conversion method. In order to fill this gap, and to obtain more accurate forecasting results, a conformable fractional non-homogenous discrete grey model (CFNDGM(1,1,α)) is proposed, and on the basis of CFNDGM model, two conformable fractional grey interval models are built. One is based on area coordinate conversion method (CFNDGM_AC), and the other is with information decomposition conversion method (CFNDGM_ID). The mathematical relationship of the two types of grey interval models is firstly given in this paper. It indicates that which type of model has better performance depends on the characteristics of original data. To assess the two fractional grey models, annal EC values in southern Jiangsu are taken as an example, and other four grey interval models are taken for comparison. Results show that CFNDGM_ID has the best performance among six models in both simulation and prediction. Then CFNDGM_ID is chosen to predict EC of southern Jiangsu in the next five years. To further improve forecasting accuracy, the optimal fitting size of CFNDGM_ID is selected. Forecasting results show that the EC in southern Jiangsu will increase in the next five years, but at a lower growth rate.

Efficient bootstrap stacking ensemble learning model applied to wind power generation forecasting

The use of wind energy plays a vital role in society owing to its economic and environmental importance. Knowing the wind power generation within a specific time window is useful for facilitating decision making in terms of maintenance, electricity market clearing, and reload sharing. However, the effect of climatic and demographic factors on wind power generation sometimes makes time series forecasting a complex task. Thus, this study evaluates an ensemble learning model that combines bagging and stacking methods applied to time series forecasting with very short-term (10 and 30-minutes) and short-term (60 and 120-minutes) evaluations of wind power generation. Arithmetic and weighted average values were used to integrate the samples from bagging strategy. The weights are defined through multi-objective optimization using a non-dominated sorting genetic algorithm – version II, aiming to enhance the forecasting accuracy and stability simultaneously. To demonstrate the wide applicability of the non-linear ensemble learning model, it is extensively tested with measurement data collected from two wind farms in Bahia State, Brazil. The experimental results show that the proposed ensemble learning model achieves a better forecasting performance than single forecasting models, such as stacking, machine learning, artificial neural networks, and statistical models, with values of approximately 7.63%, 7.58%, 20.8%, and 25%, respectively, in terms of the errors for out-of-sample forecasting reduction. In addition, results with a weighted average are 87.5% superior to those with an arithmetic average for out-of-sample wind power forecasting in the evaluated forecasting horizons. The findings show that the integration of ensemble strategies can provide accurate forecasting results in the renewable energy field.

An Outlier-Robust Point and Interval Forecasting System for Daily PM2.5 Concentration

Air pollution forecasting, particularly of PM2.5 levels, can be used not only to deliver effective warning information to the public but also to provide support for decisions regarding the control and treatment of air pollution problems. However, there are still some challenging issues in air pollution forecasting that urgently need to be solved, such as how to handle and model outliers, improve forecasting stability, and correct forecasting results. In this context, this study proposes an outlier-robust forecasting system to attempt to tackle the abovementioned issues and bridge the gap in the current research. Specifically, the system developed consists of two parts that deal with point and interval forecasting, respectively. For point forecasting, a data preprocessing module is proposed based on outlier handling and data decomposition to mitigate the negative influences of outliers and noise, which can also help the model capture the main characteristics of the original time series. Meanwhile, an outlier-robust forecasting module is designed for better modeling of the preprocessed data. For the model to further improve its accuracy, a nonlinear correction module based on an error ensemble strategy is developed that can provide more accurate forecasting results. Finally, the interval forecasting part of the system is based on a newly proposed artificial intelligence–based distribution evaluation and the results of the point forecasting part to present the range of future changes. Experimental results and analysis utilizing daily PM2.5 concentration from two provincial capital cities in China are discussed to verify the superiority and effectiveness of the system developed, which can be considered an effective technique for point and interval forecasting of daily PM2.5 concentration.

A Combined Forecasting System Based on Modified Multi-Objective Optimization for Short-Term Wind Speed and Wind Power Forecasting

Wind speed and wind power are two important indexes for wind farms. Accurate wind speed and power forecasting can help to improve wind farm management and increase the contribution of wind power to the grid. However, nonlinear and non-stationary wind speed and wind power can influence the forecasting performance of different models. To improve forecasting accuracy and overcome the influence of the original time series on the model, a forecasting system that can effectively forecast wind speed and wind power based on a data pre-processing strategy, a modified multi-objective optimization algorithm, a multiple single forecasting model, and a combined model is developed in this study. A data pre-processing strategy was implemented to determine the wind speed and wind power time series trends and to reduce interference from noise. Multiple artificial neural network forecasting models were used to forecast wind speed and wind power and construct a combined model. To obtain accurate and stable forecasting results, the multi-objective optimization algorithm was employed to optimize the weight of the combined model. As a case study, the developed forecasting system was used to forecast the wind speed and wind power over 10 min from four different sites. The point forecasting and interval forecasting results revealed that the developed forecasting system exceeds all other models with respect to forecasting precision and stability. Thus, the developed system is extremely useful for enhancing forecasting precision and is a reasonable and valid tool for use in intelligent grid programming.

An optimal integration of multiple machine learning techniques to real-time reservoir inflow forecasting

A reservoir inflow forecasting system represents a crucial technique in reservoir operation and disaster prevention, particularly in areas where the primary water source derives from typhoon events. This includes the study area of the current research, i.e., the Shihmen Reservoir (Taiwan). Effectively depositing short and high-intensity rainfall and avoiding disaster losses present significant challenges in this regard. However, the high variability and uncertainty of such rainfall events make them difficult to forecast using traditional physical-based models, which require too many calculations for application in real-time disaster forecasting. Accordingly, in this study, seven machine learning (ML) algorithms, including three conventional ML and four deep learning algorithms, were compared to derive their effectiveness for reservoir inflow forecasting in extreme weather events. The forecasting lead-times were set to 1, 4, and 6-h, representing short, medium, and long-term forecasting, respectively. Moreover, to ensure the stability and credibility of the models, two types of integrated approaches, ensemble means and switched prediction method (SP) were also employed. The results showed that although an optimal algorithm could be selected for the short, medium, and long-term, individual algorithms did not always perform well in all events. Nonetheless, the integrated approaches can effectively combine the advantages of all the included algorithms and generate more accurate and stable forecasting results, particularly when using SP, which was involved in the top three performances among all typhoon examples and indicated the best average performance. In the short-term forecast, the RMSE of the testing events is 107.2 m3/s while using SP, ranking 3rd among all 9 methods. In the medium-term forecast, the RMSE predicted by the SP is 281.72 m3/s (Rank = 1). In the long-term forecast, the SP also performed the best among the 9 methods, and the RMSE was 477.14 m3/s. In conclusion, if only single model forecast is considered, gated recurrent unit, a type of transformed recurrent neural network, will yield the best performance. Furthermore, integrated forecasts, particularly involving SP, can effectively improve the accuracy and stability of forecasts to render a model more applicable to an actual situation.

Photovoltaic power forecast based on satellite images considering effects of solar position

The rapid variation of clouds is the main factor that causes the fluctuation of photovoltaic power.11This work was supported by the National Key Research and Development Program of China under Grant 2019YFE0118400.The satellite images contain plenty of information about clouds, applicable for photovoltaic power forecast. However, in practice, two main factors obstruct the application of the satellite images: 1) the relatively low update frequency of the satellite images mismatches the photovoltaic power forecasting frequency, and 2) the cloud region that blocks the sunlight changes significantly with time. In this paper, a novel satellite image-based approach for photovoltaic power forecast is proposed to overcome these obstacles and achieve accurate forecasting results. Firstly, concerning the hourly updated satellite images, a nonlinear cloud movement forecasting model, considering the thickness and shape changes of the cloud, is presented to forecast the hourly variation of the images. Secondly, an active cloud region selection rule is derived based on the changing solar position to dynamically select the cloud region that blocks the concerned photovoltaic power station in a satellite image. Thirdly, a sequential cloud region selection algorithm is provided to estimate the intra-hour variation of the cloud to match the photovoltaic power forecasting frequency. Finally, the photovoltaic power is predicted using the XGBoost algorithm concerning the effects of the cloud and other influencing factors. Testing results show that the proposed method can achieve more accurate photovoltaic power forecasts using the low update frequency satellite images. Meanwhile, the superior performance compared with other benchmarks also verifies the effectiveness of considering cloud information obtained by the proposed method for photovoltaic power forecast.

Power System Load Forecasting Method Based on LSTM Network

Scientific load forecasting methods and accurate forecasting results are an important basis for the power system planning department work, as well as the basis and guarantee for correct decision-making on investment and construction. This paper has thoroughly studied the basic principles of recurrent neural networks and their shortcomings that they cannot solve long-term dependence problems, and a power system load forecasting method based on LSTM networks is proposed. Through the built-in two memory state lines of long term and short term, the problems that it is difficult to capture the long-term development trend and short-term fluctuation characteristics of data in time series prediction were solved. The results of case analysis show that this method can effectively improve the accuracy of power system load prediction.

Wind speed deterministic forecasting and probabilistic interval forecasting approach based on deep learning, modified tunicate swarm algorithm, and quantile regression

As a renewable, clean and economical energy source, wind energy has rapidly infiltrated into the modern power grid system. Wind speed forecasting, the crucial technology of wind power grid connection, has attracted large amounts of scholars for research and modeling. However, a large number of models only focus on the point forecasts, which are far from meeting the requirements of risk control and evaluation of power system. To fill the gap, a novel forecasting model which combined the modified multi-objective tunicate algorithm, benchmark models, and Quantile regression is proposed for deterministic and probabilistic interval forecasts. Theoretical proof demonstrates that the proposed modified algorithm can combine the merits of all benchmark models and better solve the nonlinear characteristics of wind speed. Comparative experiments which include sixteen relevant models are performed on three datasets to validate the performance of the proposed model. Simulation results show that the proposed model is the most accurate in all datasets, and can also get the interval forecast results with relatively high coverage and the narrowest width. Therefore, this model can provide accurate point forecasting results and uncertainty information, which is beneficial to the real-time control of wind turbine and power grid dispatching.

Modeling of a simplified hybrid algorithm for short-term load forecasting in a power system network

PurposeThe purpose of this paper is to develop a hybrid algorithm, which is a blend of auto-regressive integral moving average (ARIMA) and multilayer perceptron (MLP) for addressing the non-linearity of the load time series.Design/methodology/approachShort-term load forecasting is a complex process as the nature of the load-time series data is highly nonlinear. So, only ARIMA-based load forecasting will not provide accurate results. Hence, ARIMA is combined with MLP, a deep learning approach that models the resultant data from ARIMA and processes them further for Modelling the non-linearity.FindingsThe proposed hybrid approach detects the residuals of the ARIMA, a linear statistical technique and models these residuals with MLP neural network. As the non-linearity of the load time series is approximated in this error modeling process, the proposed approach produces accurate forecasting results of the hourly loads.Originality/valueThe effectiveness of the proposed approach is tested in the laboratory with the real load data of a metropolitan city from South India. The performance of the proposed hybrid approach is compared with the conventional methods based on the metrics such as mean absolute percentage error and root mean square error. The comparative results show that the proposed prediction strategy outperforms the other hybrid methods in terms of accuracy.

An Ultra-short-term Wind Power Forecasting Method with Special Error Distribution

The randomness and uncontrollability of wind energy have brought many difficulties to the development of wind power generation. How to obtain accurate forecasting results of wind power has become an increasingly important topic these years. This paper proposes an ultra-short-term wind power forecasting method using Elman neural network with an enhanced gradient descent training algorithm, which is able to compute the probabilistic distribution function (PDF) of the forecasting error by utilizing two kinds of series expansion for the purpose of regarding it as the loss function of the forecasting model. To validate the accuracy and efficiency of the purposed method, the conventional least mean square error (LMSE) based model is served as a benchmark in the comparison of simulation results. At last, historical wind power statistics of one month collected from a wind farm in the northern Hebei Province of China are used to perform single-point and probabilistic predictions in order to verify the effectiveness of the purposed method.