Synergistic cyclic optimization strategy for the data screening and forecasting of solar power, Wind power, and electricity load

A hybrid algorithm for multi-step prediction of ultra-short-term electricity load considering an innovative preprocessing method

Optimizing the design of hybrid renewable energy systems considering electric vehicle loading

Enhancing long short-term memory for electric load forecasting with multi-batch Bayesian optimization

A novel nonparametric Bayesian model for time series clustering: Application to electricity load profile characterization

Real-time efficient short-term peak load and day-ahead electricity load forecasting system using machine learning approach

In this paper, design of pumped water storage solar–hydro-power system with surface water source pumping mechanism is presented. The design considered a 750 kVA (which is 600 kW) power system that can run for 24 hours. Hence, the load profile consists of a 750 kVA by 24 hours per day electrical load which gave daily energy demand of daily energy of 14,400 kWh. The design was conducted using 21 years (2003 to 2023) meteorological dataset of the case study site at Akwa Ibom State University (AKSU) main campus at Ikot Akpadem with the latitude and longitude of 4.6214 and 7.7639 respectively. Detailed descriptive statistical analysis of the dataset was done. The design results show that the water storage capacity of is required for the 3 days of power sutonomy. About 50 water pumps each reated at 59.797 kW (approximately 60 kW) are used for the water pump while 10 water pumps each reated at 2989.827 kW (approximately3 kW) are used for the top up water segment. The hydro power with water top up has effiecncy of 0.623 (or 62.3%) and requires 23111.570 kWh of energy every day from the solar power system. The solar power is designed with the mean solar radiation value of 6.16534 and daily energy demand of 23,111.57 kWh which is the energy demand form the hydro power segment. The PV power rating is 5,174.29 kW. With 200 Wp PV module, a total of 25,871.46 PV modules were required to supply the needed power. The daily energy yield of the PV array was 31,901.29 kWh and the operating efficiency of the PV system was 0.72447 (or 72.4%). The ideas presented in this are useful for the design of modern solar hydro power plants that can be installed and sustained even in areas with water shortages.

Nowadays, 2 to 4 inverters are installed in a metro train to feed the non-traction electrical loads (auxiliary loads). Increasingly, the reliability of this Auxiliary power supply systems (APSS) is paramount, ensuring uninterrupted operation of vital subsystems such as lighting, ventilation. In this paper, a novel approach to enhance the reliability and performance of APSS is presented. Following an introduction to the conventional APSS structure, a new framework is proposed through four key steps: 1) Data input, 2) Revamped classification of auxiliary loads based on technical parameters, 3) Strategic allocation of power sources to load groups, and 4) Enhancement of reliability indices. Through a detailed case study (Tehran metro’s trains), the superiority of the new APSS is demonstrated, showcasing improved control features, heightened reliability, enhanced fault tolerance, and reduced implementation costs. The analysis and results reveals a significant improvement in reliability, with the new APSS exhibiting a maximum non-reliability rate of 15.4%, compared to 26.5% for the conventional system. Furthermore, the findings highlight the new APSS's ability to maintain power supply to high-priority load groups even after multiple faults. Finally, cost analysis indicates a more economical implementation of the new APSS, with lower equipment installation and cabling costs.

In low-voltage networks, phase-unbalanced loads are caused by the presence of single-phase consumers. Furthermore, due to the presence of railway traction substations powered by two phases in the power supply system, there is a problem of electromagnetic compatibility between the traction power supply system and the rest of the electrical power system. An unbalanced mode of operation results in additional energy losses, deterioration in power supply quality, reduced system efficiency and stability, and decreased service life of devices. For most low-voltage networks, the zero-sequence voltage asymmetry coefficient typically exceeds the requirements of power quality standards. To optimize the network operating mode with asymmetric loads, this paper proposes to apply load balancing by phases. The objective of this study is a comparative analysis of algorithms for balancing loads across phases in low-voltage networks to select the most effective one according to the criterion of minimum total costs while observing the specified restrictions on the asymmetry coefficient and voltage levels in the nodes. Materials and methods. An optimization method based on a heuristic algorithm – the particle swarm algorithm – was applied. Power flows and voltage values ​​at the nodes were calculated on a per-phase basis, taking into account active power and voltage losses. The particle swarm algorithm was implemented in the Python programming language. Results. To balance loads, two objective functions have been considered. The first function included the total network operating costs, voltage deviation at the nodes, and the zero-sequence voltage asymmetry coefficient. The second function comprised the total network operating costs and voltage deviation at the nodes. A study of two optimization algorithms has been conducted: based on sensitivity coefficients and the particle swarm algorithm; as well as solely on the particle swarm algorithm. The first algorithm comprised two stages: identifying potential nodes for balancing with the help of sensitivity coefficients, and then determining device power using the particle swarm algorithm. The second algorithm determined the device installation nodes and their power applying the particle swarm algorithm. The results obtained from the two optimization algorithms and two different objective functions have been analyzed. The values ​​of the asymmetry coefficients of zero-sequence voltage and voltages in network nodes in pre-optimization and post-optimization modes have been investigated. According to the obtained results, the lowest total costs will be achieved with two-stage optimization (with the help of sensitivity coefficients and the particle swarm algorithm). This optimization requires an objective function that includes the total cost index and the voltage deviation index at the nodes. Conclusions. When optimizing a network for load balancing, the algorithm applying sensitivity coefficients in combination with the particle swarm algorithm proves to be effective. The objective function should include total network operating costs and voltage deviations. This optimization ensures reduction of active power losses by 12.8% of the pre-optimization losses and decrease of total network operating costs.

Accurate electrical load forecasting is fundamental to the efficient operation of energy systems and plays a decisive role in both generation planning and the prevention of supply interruptions. Anticipating demand with precision enables energy generation and distribution to be adjusted effectively, reducing risks for both industrial and residential consumers. However, forecasting is challenged by climatic variations, demographic changes, and evolving consumption patterns, which limit the effectiveness of traditional approaches. Advanced machine learning techniques such as artificial neural networks have demonstrated potential to address these challenges, although their performance depends strongly on hyperparameter optimization. This study applies a multinodal forecasting methodology based on the Fuzzy ARTMAP network to predict short-term electricity demand at nine substations in New Zealand. The method involves an exhaustive search for network parameters, particularly the vigilance parameters ρa and ρb and the learning rate β, which are critical to model performance. The input data were extended with statistical measures—maximum, minimum, mean, and standard deviation—to evaluate their contribution to forecast accuracy. The results showed that the standard deviation provided the most consistent improvements among the windowing techniques, reducing the Mean Absolute Percentage Error (MAPE) in most substations. Parameter analysis further indicated that specific combinations such as ρa and β strongly influence category formation within the network, and consequently the precision of the forecasts.

The paper focuses on predicting electric load using a neural network prediction model for big data analysis. Accurate traffic flow estimation on branch roads, a crucial element for urban traffic management, is explored in the study. Traditional methods face challenges due to the high costs of equipment installation. The paper presents models that utilize main road data to indirectly estimate traffic flow, including linear and piecewise models. Additionally, the study integrates advanced techniques like genetic algorithms and Q-learning to optimize traffic signal scheduling and traffic flow forecasting. For complex intersections with multiple branch roads, the paper proposes a hybrid model combining constant, piecewise, and periodic traffic flow functions, validated through MATLAB and Python simulations. The results demonstrate that the developed models offer high accuracy in predicting traffic behavior, with a low RMSE of 2.51 and R² value of 0.9598. The models provide significant advantages in dynamic traffic environments and can be applied to optimize traffic signal control and congestion management.

Renewable energy offers a cost-effective, carbon-free solution for energy needs, while protecting the environment. Accurate forecasting of electricity generation from renewable sources is crucial for the efficiency of modern power grids. This study employs a univariate deep learning approach to predict daily renewable energy generation, evaluating Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs) as candidate models. Five performance metrics—mean absolute error, root mean squared error, mean absolute percentage error, mean absolute scaled error and the coefficient of determination—are employed to assess the forecasting power of the algorithms. The empirical results show that CNN outperforms other models, achieving an $R^2$ of almost $94\%$. This research shows that the univariate model based on historical data of electricity load generated from renewables can accurately predict day-ahead electricity load, even without meteorological data.

This study addresses the need for safer, more hygienic, and energy-efficient control of electrical loads in residential, healthcare, and industrial environments by developing a multi-switching contactless system. Conventional single-mode switching systems are limited by network dependency, restricted range, and inconsistent reliability, creating a demand for a multi-switching solution that ensures redundancy and responsive operation. The proposed system integrates an Arduino Uno as the central controller, a 433 MHz RF sensor for local wireless control, an ESP-32 Wi-Fi module for remote management, and a 5V relay module to switch multiple electrical loads. Users can operate the system via a mobile application or an RF remote, providing flexible and contactless interaction. The development involved hardware assembly, Arduino and ESP-32 firmware programming, mobile app integration, and structured testing including unit, integration, and functional evaluations to ensure performance and reliability. Experimental results demonstrated mean response times of 118 ms for RF and 176 ms for Wi-Fi control, an RF open-space range of up to 98 meters, command execution success rates of 98.5% (RF) and 97.1% (Wi-Fi), and safe load handling up to 1200 W with relay temperatures remaining below 48°C. These findings confirm that the system operates reliably under diverse conditions while maintaining low latency and thermal safety. In conclusion, the multi-switching contactless system offers a scalable, dependable, and practical solution for smart automation, enhancing hygiene, convenience, and energy management, with potential for future enhancements including voice control, improved security, and expanded load capacity.

Aiming at the problem of insufficient accuracy of power load forecasting in extreme weather, a spatio-temporally aligned database is constructed based on the multi-source data (including 15-minute-level load profiles, 0.25°×0.25° gridded meteorological data, and EM-DAT standard disaster records) for the provincial power grids in the years 2015-2023. Fifteen key indicators are screened out by the random forest algorithm, and the hybrid LSTM-XGBoost model is innovatively proposed and dynamically weighted and optimised by Lasso regression. Tests show that the RMSE of the model is controlled in the range of 2.49~3.16 under typhoon weather, and the accuracy is improved by more than 45% compared with a single model. In the extreme high temperature event in North China in 2023, the prediction error of the model 6 hours in advance is only 4.7%. The technique has been validated in actual grid operation, providing reliable decision support for extreme weather power dispatch with important engineering application value.

Addressing the data scarcity and complex consumption characteristics in mid-to-long-term electricity load forecasting for new canals, this study proposes a novel model based on navigation traffic volume cascade mapping. A multidimensional feature matrix integrating economic indicators, meteorological factors, and facility constraints is established, with canal similarity quantified via integrated constraint optimization weighting to derive multisource fusion weights. These enable freight volume prediction through feature migration using comprehensive transportation sharing. The “freight volume–lockage volume–electricity consumption” cascade then applies tonnage-based mapping to capture vessel evolution trends, generating lockage volume forecasts. Core consumption components are predicted through a mechanistic-data hybrid model for ship lock operations and a three-layer “Node–Behavior–Energy” framework for shore power system characterization, integrated with auxiliary consumption to produce the operational mid-to-long-term load forecast. Case analysis of the Pinglu Canal (2027–2050) reveals an overall “rapid-growth-then-stabilization” electricity consumption trend, where shore power’s proportion surges from 24.1% (2027) to 67.8% (2050)—confirming its decarbonization centrality—while lock system consumption declines from 28.6% to 17.2% reflecting efficiency gains from vessel upsizing and strict adherence to navigation intensity constraints.The model provides foundations for green canal energy deployment, proving essential for establishing eco-friendly waterborne logistics.

This study investigates the impact of time-varying electrical loads on household energy consumption and carbon emissions, with the goal of developing strategies for load management to reduce carbon footprints. Conducted in the residential households of San Nicolas, Ilocos Norte, Philippines, the research employed a descriptive-correlational design and a mixed-methods approach. Quantitative data on energy usage and carbon emissions were collected through electricity bills and energy monitoring devices, while qualitative insights were gathered through surveys and focus group discussions. Statistical analysis and thematic analysis were used to identify household energy consumption patterns, quantify carbon emissions during peak and off-peak hours, and evaluate strategies for shifting energy-intensive activities.

The article proposes technical means and methodological materials for determining initial data when assessing the main indicators of operational reliability of a thyristor module, which switches large currents under high voltage conditions and is one of the main elements of the switching device under load of power transformers. In addition, such designs of electrical equipment can work in the structure of various hybrid switches, as well as power units of converting equipment in the structure of energy consumption systems of energy-intensive industries. The given technical and methodological means allow determining the time and probabilistic indicators of a real thyristor module design of any structural and circuit solution, taking into account the degree and type of redundancy of its semiconductor device components. Based on the proposed methodology, it is possible to determine such initial characteristics as the parameters of the electrical load in accordance with the applied voltage and current, their changes due to load redistribution due to a change in the level of redundancy, taking into account the design features of the electrical equipment, and the operating mode of the thyristor module. The proposed methodology, together with a device for experimental study of the structure of possible failures, allows us to evaluate the main initial parameters that are necessary to determine the influence of design factors (number of semiconductor devices, principle and depth of redundancy, economic component, etc.) on the main indicators of operational reliability of thyristor modules for various purposes. As an example of the implementation of the proposed methodology, one of the options for the real design of a thyristor module in the structure of the on-load tap-changer switching device, which is operated for a long period of time in difficult conditions in the electricity consumption network of the metallurgical complex (with increased switching frequency, significant voltage and power drops, etc.), is considered. A more accurate determination of the effectiveness of the proposed methodology for establishing initial data (type and parameters of the theoretical distribution law, etc.) for determining the operational reliability indicators of the on-load tap-changer device, taking into account the load mode and features of the backup system, can be obtained by conducting additional research and experimental tests using the proposed device for a specific design of the thyristor module.

RELEVANCE. The research consists in the operational forecasting of electrical loads for both technical and economic aspects of the operation of the power system. Timely analysis of the upcoming loads allows us to determine the most efficient system operation mode, which directly affects the performance of the entire electrical complex when operating in the energy market. THE PURPOSE. To increase the accuracy of forecasting electricity consumption in the electrical complex of the grid company, providing a lower margin of error compared to current methods. METHODS. To achieve this goal, an iterative method was applied: in the Microsoft Excel environment, a sequential search and verification of existing forecasting methods was organized. RESULTS. A methodology for forecasting energy consumption by an electric utility of an energy organization has been developed. The marginal error of the proposed methodology was only 2.53%. A step-by-step algorithm for calculating the planned amount of electricity consumption by customers has been developed, ensuring consistent execution of operations to generate a comprehensive forecast. CONCLUSION. An important element of the work was the algorithm for calculating the estimated volume of electricity consumption by subscribers. This algorithm is a detailed sequence of actions necessary to implement a combined forecasting method, and also provides a systematic approach to estimating future electricity consumption, achieving a high degree of detail, which allows calculations to be performed without using specialized software, using only basic engineering calculation methods.

With the evolution of smart grids, accurate and secure predictions of the electricity load become crucial for efficient energy management and reliability. In this paper, a scalable and cyber-resilient methodology for electricity consumption forecasting on individual smart meter level based on machine learning and anomaly detection schemes is proposed. The proposed technique utilizes K-MEANS Clustering and Neural Networks (KMEANS–NN) to enhance Individual Load Forecasting (ILF) with reduced computational complexity and high prediction accuracy. A Principal Component Analysis based One-Class Support Vector Machine (PCA–OCSVM) model is employed as an Anomaly Detection Scheme (ADS) to identify the false data injection attacks in smart meter telemetry. The system uses five months of real-world data from :text{2,089} smart meters gathered under the supervision of Electrical Distribution Sector (EDS) of Suez Canal Authority (SCA) in Egypt. KMEANS–NN strategy reduces significantly MAAPE by up to :25.6% and cuts computational time from days to minutes. It improves forecasting accuracy across four proposed models: ARIMA, CTREE, MLP and NNETAR. To assess the cyber-security profile, :50% of the dataset is orchestrated with scaling, ramping and random cyber-attack simulation. Proposed ADS achieves :99.3% overall accuracy, :100% sensitivity, :98.62% precision, :98.6% specificity and F1-score of::0.9896, whereas it’s :100% accurate on clean data. This integrated model offers accurate, efficient, and secure load forecasting presenting good potential for its deployment in large-scale smart grid environments.

Thermal compression bonding (TCB) electrodes that initiate thermal fatigue cracks compromise reliability and takt time in electronic manufacturing, and accurate prediction of three-dimensional (3D) electrode cracks is a prerequisite for crack mitigation. This study developed a digital twin (DT) framework that combined physics-based simulation and artificial intelligence (AI). The framework used the extended finite element method (XFEM) to build a high-fidelity electrode DT and reproduced fatigue behavior under coupled electrical, thermal, and mechanical loading through adaptive updating. To alleviate the scarcity of crack data, a conditional variational autoencoder (CVAE) with a position attention (PA) mechanism was constructed, with an error of 0.7% to 1.3% relative to experimental results. Using the augmented data, the PA-RePointNet model was developed to predict 3D crack morphology. Results showed that PA-RePointNet surpassed PointNet++ and PointCNN in prediction accuracy and stability and achieved a mean absolute error (MAE) of 2.8, a root mean square error (RMSE) of 5.1, and a coefficient of determination (R²) of 0.9378, while the maximum relative error between the reconstructed 3D cracks and experimental measurements was 1.87%. This framework provides a high-precision solution for electrode crack prediction and opens a new pathway for intelligent maintenance of TCB electrodes in microelectronic manufacturing.