Short-term Power Research Articles

Optimized extreme learning machine using genetic algorithm for short-term wind power prediction

Through the much defiance facing energy today, it has become necessary to rely on wind energy as a source of unlimited renewable energies. However, energy planning and regulation require wind capacity forecasting, because oscillations of wind speed drastically affect directly power generation. Therefore, several scenarios must be provided to allow for estimating uncertainties. To deal with this problem, this paper exploits the major advantages of the regularized extreme learning machine algorithm (R-ELM) and thus proposes a model for predicting the wind energy generated for the next hour based on the time series of wind speed. The R-ELM is combined with the genetic algorithm which is designed to optimize the most important hyperparameter which is the number of hidden neurons. Thus, the proposed model aims to forecast the average wind power per hour based on the wind speed of the previous hours. The results obtained showed that the proposed method is much better than those reported in the literature concerning the precision of the prediction and the time convergence.

Short-term photovoltaic power forecasting with feature extraction and attention mechanisms

The uncertainty of weather conditions has always been a major challenge limiting the performance of photovoltaic (PV) power prediction. Enhancing the accuracy and stability of PV power prediction is crucial for optimizing grid operation. In response to this challenge, this study introduces a hybrid model that integrates an attention mechanism with the Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory Network (BiLSTM). This model aims to mitigate the adverse impact of weather variability on the accuracy of PV power prediction by effectively extracting key features from multidimensional time series data. Additionally, through ablation experiments, this research further assesses the contribution of each model component to performance. Validated with actual data collected from a 1 MW PV power station in China, our proposed model demonstrates significant performance advantages compared to eight advanced prediction models. Ablation study results reveal that removing the CNN component led to a 58.2% increase in MAE and a 53.9% increase in RMSE, while the removal of the attention mechanism resulted in an 83.8% increase in maximum error. These findings underscore the substantial enhancement in prediction accuracy achieved through the integration of CNN and BiLSTM, and the introduction of the attention mechanism significantly boosts the model's prediction stability.

Scaling considerations and optimal control for an offshore wind powered direct air capture system

The optimal design and operation of an offshore wind powered direct air capture (DAC) system is complex owing to the intermittent energy supply and the modularity of the units. A solid amine DAC process involves multiple individual units which undergo periodic loading to capture carbon dioxide (CO2) from ambient air, followed by regeneration to produce pure CO2 for utilisation or sequestration. The modular nature of a solid DAC process is exploited in this study to investigate the optimal design and coordinated operation of multiple DAC units mounted on a single 15 MW offshore wind turbine platform, with battery energy storage for additional short term power buffering. Important design parameters considered include the number of independently controllable units, the cyclic capacity of each unit (proportional to the amount of adsorbent) and the battery capacity and maximum power ratings. The design study results highlighted the diminishing returns to the CO2 capture rate with scaling, with a full design optimisation based upon cost estimations left for future work as the technology matures. It was found the optimal configuration was 14 DAC units, each with a cyclic capacity of 2000 kg CO2 , giving a total annual capture rate of 45 600 ton yr−1 and a wind utilisation factor of 96.6%. Furthermore, it was found that a rules-based control strategy based on high and low loading limits was competitive with a machine learning based controller and outperformed a model predictive control scheme.

Power Demand Forecasting Using ANN and Prophet Models for the Load Despatch Center in Andhra Pradesh, India

This paper uses various data variables to develop and analyze ANN and Prophet models for power demand forecasting in Andhra Pradesh, India. The electricity power consumption in Andhra Pradesh was about 51,756.000 GWh in 2021. Currently, there is a great emphasis on saving power. Power Demand Forecasting is creating much interest, and many models, such as artificial neural networks combined with other techniques based on real-life phenomena, are used and tested. These models have become an essential part of the power and energy sector. This paper considered specific time-series analysis methods and deep-learning techniques for short-term power demand forecasting. This paper also analyzes and compares results between the prophet and ANN models to predict power demand in Andhra Pradesh, India. Our results comparatively revealed the model's appropriateness for the problem. Both models performed well in three performance metrics: accuracy, generalization, and robustness. However, the AI model exhibits better accuracy than Prophet for the historical data set. The time taken for model fitting is also comparatively less for the AI models. The forecast accuracy of the electricity was in the range of 95 to 97.65.

Short-term wind power output prediction using hybrid-enhanced seagull optimization algorithm and support vector machine: A high-precision method

ABSTRACT Affected by the uncertainty of external environmental factors, wind power generation has significant characteristics of randomness and non-stationarity. Accurately predicting wind power is a necessary technical means to improve the efficiency of wind energy utilization and reduce wind abandonment. Integrating large-scale wind power into the grid has put higher requirements for wind power prediction accuracy. Hence, this study proposes a combined prediction model based on wavelet denoising (WD), hybrid enhanced seagull optimization algorithm (HESOA) and support vector machine (SVM) to predict short-term wind power. The WD technology obtains effective signals from original wind power data, providing a reasonable basis for prediction research. The HESOA is proposed by introducing the Tent mapping, individual self-learning factor and Gaussian population strategy into the original seagull optimization algorithm to optimize SVM’s prediction ability. The case study results reflect that the prediction method is feasible and universal in suppressing wind power generation volatility in spring and winter. The RMSE of short-term wind power prediction is controlled below 65 kW, and the value of R2 is above 98%. This study improves the accuracy of wind power prediction and helps to strengthen the renewable energy consumption level and reliability of wind power grid-connected generation systems.

Short-term wind power forecasting through stacked and bi directional LSTM techniques.

Computational intelligence (CI) based prediction models increase the efficient and effective utilization of resources for wind prediction. However, the traditional recurrent neural networks (RNN) are difficult to train on data having long-term temporal dependencies, thus susceptible to an inherent problem of vanishing gradient. This work proposed a method based on an advanced version of RNN known as long short-term memory (LSTM) architecture, which updates recurrent weights to overcome the vanishing gradient problem. This, in turn, improves training performance. The RNN model is developed based on stack LSTM and bidirectional LSTM. The parameters like mean absolute error (MAE), standard deviation error (SDE), and root mean squared error (RMSE) are utilized as performance measures for comparison with recent state-of-the-art techniques. Results showed that the proposed technique outperformed the existing techniques in terms of RMSE and MAE against all the used wind farm datasets. Whereas, a reduction in SDE is observed for larger wind farm datasets. The proposed RNN approach performed better than the existing models despite fewer parameters. In addition, the approach requires minimum processing power to achieve compatible results.

Twin proximal support vector regression with heteroscedastic Gaussian noise

Twin proximal support vector regression, a novel approach, merges twin support vector regression (TSVR) with proximal support vector regression (PSVR) for regression analysis. Classical PSVR and TSVR assume that the data noise follows a homoscedastic Gaussian distribution with zero mean. However, in the real world, such as short-term wind speed prediction and wind farm power generation prediction, noise tends to follow a heteroscedastic Gaussian distribution with zero mean. Therefore, based on the aforementioned model framework and added the heteroscedastic noise feature, we develop a novel regression model named the twin proximal support vector regression model with heteroscedastic Gaussian noise (TPSVR-HGN). The Augment Lagrange multiplier approach is used to solve the proposed TPSVR-HGN model. On the artificial dataset and the real world dataset, compared with recent advanced models, the prediction accuracy of the TPSVR-HGN model has been improved by about 7% and 11% respectively. As the results of this experiment indicate, our method is effective and feasible.

An analogue on/off state-switching control method suitable for inverter-based air conditioner load cluster participating in demand response

With the significant trend towards variable frequency in heating ventilating and air-conditioner (HVAC) loads, the inverter-based air conditioner load (IACL) clusters are poised to become the mainstay in participating in demand response (DR). During the process of DR, once the indoor temperature exceeds the comfort constraint, HVAC load must be forced to exit DR, which brings correlation to the behaviour of the preceding and following periods, making cluster optimization modelling and solution difficult. In order to solve the problems, this paper proposes an analogue ON/OFF state-switching (AOSS) control method suitable for IACL cluster participating in DR. Firstly, the critical working point corresponding to the comfort constraint is analysed for eliminating the temporal coupling for IACL. Then, an AOSS control method is proposed based on the critical point analysis. The feasibility of the proposed AOSS control is validated by the experimental results, with the Hisense KFR-75W/T08SBp-A2 inverter-based air conditioning DR experimental platform. Furthermore, by using the proposed AOSS control, a day-ahead scheduling model is constructed, and, the traditional state-queuing (SQ) model is transplanted to the IACL cluster for short-term power control. And the case studies verified the effectiveness and applicability of the day-ahead scheduling model and the transplanted SQ model.

A hybrid deep learning model with an optimal strategy based on improved VMD and transformer for short-term photovoltaic power forecasting

The precise forecasting of photovoltaic (PV) power is important for efficient grid management. To enhance the analysis and processing capability of PV characteristics, address the feature extraction challenges for long sequences, and improve forecasting accuracy, this study presents a robust hybrid deep learning model for PV power forecasting. First, a dynamic mean pre-processing algorithm is applied for data cleaning. Subsequently, an improved whale variational mode decomposition (IWVMD) algorithm is proposed for data decomposition in multichannel multi-scale modeling. Furthermore, a novel context-embedded causal convolutional Transformer (CCTrans) structure is used to predict each subsequence, and an optimal strategy is formulated for both input and output under the combined dynamic contextual information and single target variable forecasting (CDCTF) pattern. Finally, the forecasting results are reconstructed. Experiments are conducted to evaluate the performance of the model across different seasons, using publicly available datasets from the Desert Knowledge Australia Solar Center (DKASC). Ablation studies, validation with diverse datasets, and comparisons with other models confirm the effectiveness, accuracy, robustness, and generalizability of the model. In addition, recommendations for optimal forecasting ranges for different seasons are provided.

Financial Market Development and Foreign Portfolio Investments in Nigeria and South Africa

The study investigates the effect of financial market development on foreign portfolio investment in Nigeria and South Africa between the periods of first quarter in 1995 to fourth quarter of 2022. The study employs an ex-post factor research design, the study deploys panel autoregressive distributed lag modelling. The inferences were made at 5% significant level. Findings from the study reveal that lagged Portfolio Investment is not statistically significant to foreign portfolio investment (coefficient = -0.5026613, p-value = 0.275), in contrast, lagged Stock Market Turnover Ratio has a significant positive coefficient (coefficient = 0.5696119, p-value < 0.000), indicating a positive short-term relationship with changes in Portfolio Investment. However, other lagged variables like Stock Market Capitalization, All Share Index, Broad Money Supply, and Real Credit to the Private Sector show coefficients without statistical significance, suggesting limited short-term predictive power. In the long run, the adjusted term for lagged Portfolio Investment exhibits a highly significant negative effect (coefficient = -1.502661, p-value = 0.001). Lagged Broad Money Supply and Real Credit to the Private Sector also lack statistical significance in the long term, while lagged Stock Market Turnover Ratio and All Share Index have statistically significant positive coefficients. However, Stock Market Capitalization lacks statistical significance in predicting long-term changes in foreign Portfolio Investment. In respect to the result, the study recommended that policy makers should implement measures to enhance transparency and regulation within financial markets to promote investor confidence and attract foreign capital inflows. This may include strengthening regulatory frameworks, improving reporting standards, and ensuring effective oversight mechanisms.

Ultra short term power load forecasting based on the fusion of Seq2Seq BiLSTM and multi head attention mechanism.

Ultra-short-term power load forecasting is beneficial to improve the economic efficiency of power systems and ensure the safe and stable operation of power grids. As the volatility and randomness of loads in power systems, make it difficult to achieve accurate and reliable power load forecasting, a sequence-to-sequence based learning framework is proposed to learn feature information in different dimensions synchronously. Convolutional Neural Networks(CNN) Combined with Bidirectional Long Short Term Memory(BiLSTM) Networks is constructed in the encoder to extract the correlated timing features embedded in external factors affecting power loads. The parallel BiLSTM network is constructed in the decoder to mine the power load timing information in different regions separately. The multi-headed attention mechanism is introduced to fuse the BiLSTM hidden layer state information in different components to further highlight the key information representation. The load forecastion results in different regions are output through the fully connected layer. The model proposed in this paper has the advantage of high forecastion accuracy through the example analysis of real power load data.

A short-term forecasting method for photovoltaic power generation based on the TCN-ECANet-GRU hybrid model

Due to the uncertainty of weather conditions and the nonlinearity of high-dimensional data, as well as the need for a continuous and stable power supply to the power system, traditional regression analysis and time series forecasting methods are no longer able to meet the high accuracy requirements of today's PV power forecasting. To significantly improve the prediction accuracy of short-term PV output power, this paper proposes a short-term PV power forecasting method based on a hybrid model of temporal convolutional networks and gated recurrent units with an efficient channel attention network (TCN-ECANet-GRU) using the generated data of an Australian PV power station as the research object. First, temporal convolutional networks (TCNs) are used as spatial feature extraction layers, and an efficient channel attention network (ECANet) is embedded to enhance the feature capture capability of the convolutional network. Then, the GRU is used to extract the timing information for the final prediction. Finally, based on the experimental validation, the TCN-ECANet-GRU method generally outperformed the other baseline models in all four seasons of the year according to three performance assessment metrics: the normalized root mean square error (RMSE), normalized mean absolute error (MAE) and coefficient of determination (R2). The best RMSE, MAE and R2 reached 0.0195, 0.0128 and 99.72%, respectively, with maximum improvements of 11.32%, 8.57% and 0.38%, respectively, over those of the suboptimal model. Therefore, the model proposed in this paper is effective at improving prediction accuracy. Using the proposed method, this paper concludes with multistep predictions of 3, 6, and 9 steps, which also indicates that the proposed method significantly outperforms the other models.

Short-term power load forecasting method based on Bagging-stochastic configuration networks.

Accurate short-term load forecasting is of great significance in improving the dispatching efficiency of power grids, ensuring the safe and reliable operation of power grids, and guiding power systems to formulate reasonable production plans and reduce waste of resources. However, the traditional short-term load forecasting method has limited nonlinear mapping ability and weak generalization ability to unknown data, and it is prone to the loss of time series information, further suggesting that its forecasting accuracy can still be improved. This study presents a short-term power load forecasting method based on Bagging-stochastic configuration networks (SCNs). First, the missing values in the original data are filled with the average values. Second, the influencing factors, such as the weather- and week-type data, are coded. Then, combined with the data of influencing factors after coding, the Bagging-SCNs integration algorithm is used to predict the short-term load. Finally, by taking the daily load data of Quanzhou City, Zhejiang Province as an example, the program of the abovementioned method is compiled in Python language and then compared with the long short-term memory neural network algorithm and the single-SCNs algorithm. Simulation results show that the proposed method for medium- and short-term load forecasting has a high forecasting accuracy and a significant effect on improving the accuracy of load forecasting.

A short-term wind power prediction approach based on an improved dung beetle optimizer algorithm, variational modal decomposition, and deep learning

Accurate short-term wind power prediction is crucial for the efficient and safe operation of wind power systems. To enhance the accuracy of short-term wind power prediction, this paper proposes a hybrid short-term wind power prediction model, IDBO-VMD-TCN-GRU-Attention, based on the Improved Dung Beetle Optimizer algorithm (IDBO), Variational Modal Decomposition (VMD), Temporal Convolutional Network (TCN), Gated Recurrent Unit (GRU), and Attention Mechanism. The IDBO is used to optimize the parameters of the VMD. Then the optimized IDBO-VMD is used to decompose the original data into modal components with lower volatility to fully extract the data features. These modal components are inputted into the TCN-GRU-Attention to predict the short-term wind power and obtain the final prediction value. The model is tested and validated using real data from four different months and compared against 11 other models. Results demonstrate that our proposed model significantly reduces the Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) by an average of at least 22.86 %, 18.82 %, and 19.99 %, respectively, across the four different months. This indicates that the proposed model provides a superior fit to the data, offers higher prediction accuracy, and holds significant practical value.

A novel Bagged-CNN architecture for short-term wind power forecasting

ABSTRACT Wind power forecasting plays a pivotal role in ensuring the dependable integration of wind energy into power grids. This research introduces a novel Bagged-CNN architecture tailored for short-term wind power forecasting. This architecture harnesses the combined strengths of the Bagging ensemble technique and Convolutional Neural Networks (CNN) to enhance prediction accuracy and robustness. Our approach demonstrates superior forecasting capabilities by exploiting the spatial and temporal features captured by CNNs. To validate our proposed architecture, we have conducted a comprehensive evaluation across three distinct wind farms, each characterized by unique geographical and climatic conditions. We systematically compared the performance of our Bagged-CNN model against several standalone machine-learning algorithms commonly employed in wind power forecasting. The hyperparameters of our Bagged-CNN model are meticulously optimized using the GRID search algorithm, which systematically explores a predefined parameter space. Notably, our predictions shed light on the substantial impact of training data period length on wind power prediction accuracy. Our research underscores the potential of coupling Bagging and CNN techniques for short-term wind power forecasting. The Bagged-CNN architecture, as proposed, serves as a robust framework for capturing intricate spatial and temporal patterns in wind power data, thereby facilitating more precise and dependable predictions.

Short-term photovoltaic power forecasting using parameter-optimized variational mode decomposition and attention-based neural network

ABSTRACT Photovoltaic power generation is impacted by various meteorological factors leading to significant intermittent and volatile, so dispatch of photovoltaic power plants and safe operation of power systems hinge on accurate prediction of PV power output. Researchers have proposed a variety of ways to improve the performance of predictions, and a hybrid model often performs better than a single model. Considering that the sequence decomposition method can alleviate the volatile nature of the original sequence, we propose a new hybrid model VMD-GA-Conv-A-LSTM, design a method to determine the optimal parameters of the VMD and utilize the parameter-optimized VMD for sequence decomposition, combining with a novel deep learning model for more accurate prediction. The model first calculates the optimal parameters for the variational mode decomposition (VMD) using a search algorithm over a specified parameter range, and uses these parameters to decompose the photovoltaic power sequence into several sub-sequences. Then, the sub-sequences and preprocessed historical meteorological data are input into several long short-term memory (LSTM) integrated with 1D convolution and attention mechanism (Conv-A-LSTM) separately. The predictions corresponding to each sub-sequence are accumulated to get the predictions of the hybrid model. The hybrid model was validated on the dataset generated from the 5.20 kW Photovoltaic site in Alice Springs, Australia, and ERA5 data, respectively. Compared with baseline models, the proposed hybrid model achieves the best prediction accuracy. The RMSE, MAE, and R2 of the 2-hour prediction performed on the Australia dataset are 0.1884 kW, 0.0758 kW and 0.9876, respectively. Therefore, the hybrid model proposed in this study is able to provide statistical data support for photovoltaic plant operation and scheduling.

Optimizing Short-Term Photovoltaic Power Forecasting: A Novel Approach with Gaussian Process Regression and Bayesian Hyperparameter Tuning

The inherent volatility of PV power introduces unpredictability to the power system, necessitating accurate forecasting of power generation. In this study, a machine learning (ML) model based on Gaussian process regression (GPR) for short-term PV power output forecasting is proposed. With its benefits in handling nonlinear relationships, estimating uncertainty, and generating probabilistic forecasts, GPR is an appropriate approach for addressing the problems caused by PV power generation’s irregularity. Additionally, Bayesian optimization to identify optimal hyper-parameter combinations for the ML model is utilized. The research leverages solar radiation intensity data collected at 60-min and 30-min intervals over periods of 1 year and 6 months, respectively. Comparative analysis reveals that the data set with 60-min intervals performs slightly better than the 30-min intervals data set. The proposed GPR model, coupled with Bayesian optimization, demonstrates superior performance compared to contemporary ML models and traditional neural network models. This superiority is evident in 98% and 90% improvements in root mean square errors compared to feed-forward neural network and artificial neural network models, respectively. This research contributes to advancing accurate and efficient forecasting methods for PV power output, thereby enhancing the reliability and stability of power systems.

Short term power load forecasting system based on improved neural network deep learning model

AbstractThe electricity load prediction is closely related to production and daily life. The electricity load prediction is also a very important task. With the widespread application of smart grids, load data shows an exponential growth trend. The huge amount of data in the load makes power prediction even more difficult. On the basis of traditional prediction algorithms, a power load prediction model based on machine learning and neural networks is designed. Because the single model prediction has the unstable results, a combined model is obtained based on the ensemble learning idea and two single model prediction method. The prediction results are detected by the load data. From the experimental results, the mean absolute percentage error (MAPE) of the AdaBoost‐GRU data fusion model is 0.066%. Compared to the AdaBoost‐GRU data fusion model, the MAPE decreases by 1.59% and 1.12%, respectively. The relative mass scores of the two groups decrease by 132.57% and 89.14%, respectively. The prediction accuracy is improved, which has advantages compared to traditional combination models. It can effectively enhance the accuracy of short‐term power grid load forecasting. It is an important scientific and practical reference for power grid decision‐making.

Design and implementation of controlled load damping factor controller in series connection for power systems with high penetration of renewable energy

As sustainable natural sources such as wind and solar are increasingly integrated into power grids, conventional fossil fuel-based generating units will be gradually replaced, resulting in enormous pressure on frequency regulation of the novel power systems. This paper proposes a method for implementing a cascaded load-damping factor controller based on the controlled load-damping factor controller. Series-type voltage regulators, namely, solid-state transformers or dynamic voltage restorers, can regulate the voltage of the 10 kV feeder within the allowed range. Therefore real-time control of composite load power is realized, which significantly improves the primary frequency regulation capability of novel power systems with renewable energy generation(REG). The effect of actuator regulation time constant is considered, The impact of dynamic loads on the primary frequency regulation of the controller, designed based on a static load model, is analyzed, The effectiveness of the controller on the primary frequency regulation under different renewable energy penetration rates is discussed, The effectiveness of the controller in smoothing short-term power fluctuations of REG is examined. Finally, the effectiveness of the series-connected controlled load-damping factor controller in primary frequency regulation is verified on the RTDS simulation experimental platform. The proposed control system is characterized by a simple structure, easy implementation, and convenient maintenance, which can realize the coordination and unification of reactive-voltage and active-frequency control of the novel power system in the 110 kV customer substation and is beneficial to practical application in engineering.

Short-term photovoltaic power prediction model based on hierarchical clustering of K-means++ algorithm and deep learning hybrid model

In order to further improve the accuracy of photovoltaic (PV) power prediction and the stability of power system, a short-term PV power prediction model based on hierarchical clustering of K-means++ algorithm and deep learning hybrid model is proposed in this paper. First, hierarchical clustering of the K-means++ algorithm is used to cluster historical data into different weather scenes according to different seasons. Second, a hybrid model combining convolutional neural network (CNN), squeeze-and-excitation attention mechanism (SEAM), and bidirectional long short-term memory (BILSTM) neural network is constructed to capture long-term dependencies in time series, and the improved pelican optimization algorithm (IPOA) is used to optimize the hyperparameters in the prediction model. Finally, an example for modeling analysis is conducted by using the actual output and meteorological data of a PV power station in the Ili region of Xinjiang, China. The effectiveness and accuracy of the proposed model are verified by comparing with LSTM, BILSTM, CNN-BILSTM, and POA-CNN-SEAM-BILSTM models, and the superiority of IPOA is verified by comparing with particle swarm optimization and whale optimization algorithm. The results show that the proposed model can obtain better results under different weather scenes in different seasons, and the prediction accuracy of the model optimized by IPOA is further improved.