Load Prediction Model Research Articles

Impact of data for forecasting on performance of model predictive control in buildings with smart energy storage

Data is required to develop forecasting models for use in Model Predictive Control (MPC) schemes in building energy systems. However, data is costly to both collect and exploit. Determining cost optimal data usage strategies requires understanding of the forecast accuracy and resulting MPC operational performance it enables. This study investigates the performance of both simple and state-of-the-art machine learning prediction models for MPC in multi-building energy systems using a simulated case study with historic building energy data. The impact on forecast accuracy of measures to improve model data efficiency is quantified, specifically for: reuse of prediction models, reduction of training data duration, reduction of model data features, and online model training. A simple linear multi-layer perceptron model is shown to provide equivalent forecast accuracy to state-of-the-art models, with greater data efficiency and generalisability. The use of more than 2 years of training data for load prediction models provided no significant improvement in forecast accuracy. Forecast accuracy and data efficiency were improved simultaneously by using change-point analysis to screen training data. Reused models and those trained with 3 months of data had on average 10% higher error than baseline, indicating that deploying MPC systems without prior data collection may be economic.

Force magnitude and distribution during impacts to the hip are affected differentially by body size and body composition

Hip fractures are a severe health concern among older adults. While anthropometric factors have been shown to influence hip fracture risk, the low fidelity of common body composition metrics (e.g. body mass index) reduces our ability to infer underlying mechanisms. While simulation approaches can be used to explore how body composition influences impact dynamics, there is value in experimental data with human volunteers to support the advancement of computational modeling efforts. Accordingly, the goal of this study was to use a novel combination of subject-specific clinical imaging and laboratory-based impact paradigms to assess potential relationships between high-fidelity body composition and impact dynamics metrics (including load magnitude and distribution and pelvis deflection) during sideways falls on the hip in human volunteers.Nineteen females (<35 years) participated. Body composition was assessed via DXA and ultrasound. Participants underwent low-energy (but clinically relevant) sideways falls on the hip during which impact kinetics (total peak force, contract area, peak pressure) and pelvis deformation were measured. Pearson correlations assessed potential relationships between body composition and impact characteristics.Peak force was more strongly correlated with total mass (r = 0.712) and lean mass indices (r = 0.510–0.713) than fat mass indices (r = 0.401–0.592). Peak deflection was positively correlated with indices of adiposity (all r > 0.7), but not of lean mass. Contact area and peak pressure were positively and negatively associated, respectively, with indices of adiposity (all r > 0.49). Trochanteric soft tissue thickness predicted 59 % of the variance in both variables, and was the single strongest correlate with peak pressure. In five-of-eight comparisons, hip-local (vs. whole body) anthropometrics were more highly associated with impact dynamics.In summary, fall-related impact dynamics were strongly associated with body composition, providing support for subject-specific lateral pelvis load prediction models that incorporate soft tissue characteristics. Integrating soft and skeletal tissue properties may have important implications for improving the biomechanical effectiveness of engineering-based protective products.

Bi-Level Planning of Electric Vehicle Charging Stations Considering Spatial–Temporal Distribution Characteristics of Charging Loads in Uncertain Environments

With the increase in the number of distributed energy resources (DERs) and electric vehicles (EVs), it is particularly important to solve the problem of EV charging station siting and capacity determination under the distribution network considering a large proportion of DERs. This paper proposes a bi-level planning model for EV charging stations that takes into account the characteristics of the spatial–temporal distribution of charging loads under an uncertain environment. First, the Origin–Destination (OD) matrix analysis method and the real-time Dijkstra dynamic path search algorithm are introduced and combined with the Larin Hypercube Sampling (LHS) method to establish the EV charging load prediction model considering the spatial and temporal distribution characteristics. Second, the upper objective function with the objective of minimizing the cost of EV charging station planning and user charging behavior is constructed, while the lower objective function with the objective of minimizing the cost of distribution network operation and carbon emission cost considering the uncertainty of wind power and photovoltaics is constructed. The constraints of the lower-layer objective function are transformed into the upper-layer objective function through Karush–Kuhn–Tucker (KKT) conditions, the optimal location and capacity of charging stations are finally determined, and the model of EV charging station siting and capacity determination is established. Finally, the validity of the model was verified by planning the coupled IEEE 33-node distribution network with the traffic road map of a city in southeastern South Dakota, USA.

Vision-based estimation method of crowd-induced vertical dynamic loading and vibration analysis

Most existing studies concentrating on human-induced loads on structures often rely on approximate formulas based on the loading from a single gait cycle, which inherently possess certain limitations. In this paper, a novel approach utilizing a multi-person 2D posture estimation model rooted in computer vision technology to real-time identify the posture of moving human bodies on construction sites is proposed. This approach works to deduce the reaction forces of moving bodies upon the floor by analyzing the motion characteristics of different body parts during their movement, ensuring an accurate estimation of structural loading. To validate the model’s accuracy, a series of tests were conducted, leveraging force measurement equipment to scrutinize the precision of load estimation during single-person motion. This examination seeks to ascertain the potential of the load prediction model in forecasting multi-person loads within actual project environments.

Research on Load Estimation for Commercial Trucks Based on Air Suspension State Parameters

For commercial trucks, accurate vehicle load information is crucial to preventing overloading and uneven load distribution, thereby improving transportation efficiency and reducing transportation costs. Existing research on vehicle load estimation primarily focuses on tires, axles, frames, and leaf springs, with limited studies on load estimation for vehicles equipped with air suspension. This paper presents the design of a vehicle onboard weighing system for civil commercial trucks based on the state parameters of air springs and proposes a matching method for vehicle load estimation. The system utilizes laser distance- and gas pressure sensors to collect the state parameters of the air springs. It estimates the vehicle load and displays the load information in real time on the onboard display. The vehicle load estimation method was explored through prototype testing and theoretical derivation. A fitting model was constructed using surface fitting techniques to establish the relationship between the effective contact area and the height variation and capsule pressure of the air spring. Subsequently, a load prediction model was built based on the force equilibrium equation of the air springs. Finally, the construction and accuracy of the load prediction model for a specific type of diaphragm air spring were verified using finite element analysis. The results demonstrated that the average relative error of the load prediction model could be controlled within 1%, meeting the high accuracy requirements of the vehicle weighing system.

A multi-stage LSTM federated forecasting method for multi-loads under multi-time scales

For multiple integrated energy systems with similar energy using behavior, the federated learning mechanism can build a higher precision multivariate load prediction model for each integrated energy system. However, the data of different loads in these systems often have different time scales, limited by the characteristics and frequency of data acquisition equipment. Systems often set different hyperparameters with each other to ensure prediction accuracy, which makes it difficult to use federated learning for co-training. In this paper, a multi-stage Long Short-Term Memory (LSTM) federated model based on interpolation method is proposed for multi-node multivariate load forecasting on multi-time scales. In the first stage, the load data of larger time scales are interpolated to unify all the load data to the same time scale. In the second stage, each node (i.e., each integrated energy system) uses its own data to carry out multivariate load training and establish its multivariate load forecasting model. In the third stage, based on the federated learning mechanism and fine-tuning strategy, the LSTM federated prediction of multiple loads is established by fusion training between nodes. Experimental results show that the proposed method can obtain higher precision multi-source load prediction results for multiple integrated energy systems.

Multivariate time series ensemble model for load prediction on hosts using anomaly detection techniques

Multivariate time series ensemble model for load prediction on hosts using anomaly detection techniques

An Improved CNN-BILSTM Model for Power Load Prediction in Uncertain Power Systems

Power load prediction is fundamental for ensuring the reliability of power grid operation and the accuracy of power demand forecasting. However, the uncertainties stemming from power generation, such as wind speed and water flow, along with variations in electricity demand, present new challenges to existing power load prediction methods. In this paper, we propose an improved Convolutional Neural Network–Bidirectional Long Short-Term Memory (CNN-BILSTM) model for analyzing power load in systems affected by uncertain power conditions. Initially, we delineate the uncertainty characteristics inherent in real-world power systems and establish a data-driven power load model based on fluctuations in power source loads. Building upon this foundation, we design the CNN-BILSTM model, which comprises a convolutional neural network (CNN) module for extracting features from power data, along with a forward Long Short-Term Memory (LSTM) module and a reverse LSTM module. The two LSTM modules account for factors influencing forward and reverse power load timings in the entire power load data, thus enhancing model performance and data utilization efficiency. We further conduct comparative experiments to evaluate the effectiveness of the proposed CNN-BILSTM model. The experimental results demonstrate that CNN-BILSTM can effectively and more accurately predict power loads within power systems characterized by uncertain power generation and electricity demand. Consequently, it exhibits promising prospects for industrial applications.

Efficient prediction of tidal turbine fatigue loading using turbulent onset flow from Large Eddy Simulations

To maximise the availability of power extraction from a tidal stream site, tidal turbines need to be able to operate reliably when located within arrays. This requires a thorough understanding of the operating conditions, which include turbulence, velocity shear due to bed proximity and roughness, ocean waves and due to upstream turbine wakes, over the range of flow speeds that contribute to the loading experienced by the devices. High-fidelity models such as Large Eddy Simulation (LES) can be used to represent these complex flow conditions and turbine device models can be embedded to predict loading. However, to inform micro-siting of multiple turbines with an array, the computational cost of performing multiple simulations of this type is impractical. Unsteady onset conditions can be generated from the LES to be used in an offline coupling fashion as input to lower-fidelity load prediction models to enable computationally efficient array design. In this study, an in-house Blade Element Momentum (BEM) method is assessed for prediction of the unsteady loads on the turbines of a floating tidal device with unsteady inflow developed with the in-house LES solver DOFAS. Load predictions are compared to those obtained using the same unsteady inflow to the commercial tool Tidal Bladed and from an Actuator Line Model (ALM) embedded in the LES solver. Estimates of fatigue loads differ by up to 3% for mean thrust and 11% for blade root bending moment for a turbine subject to a turbulent channel flow. When subjected to more complex flows typical of a turbine wake, the predictions of rotor thrust fatigue differ by up to 10%, with loads reduced by the inclusion of a pitch controller.

Construction of a recurrent neural network-based electrical load forecasting model for a 110 kV substation: a case study in the Western Region of The Republic of Kazakhstan

This paper presents an approach for using a long short-term memory (LSTM)-based recurrent neural network with various configurations to construct a forecasting model for electrical load prediction of a 110 kV substation. The issues of unbalances arising in energy management systems due to discrepancies between generated and consumed energy can lead to power outages and blackouts. With the introduction of the most accurate forecasts, the task of maintaining electrical reliability for grid operators can be greatly simplified. Through an investigation into 81 different parameter combinations, the research revealed the optimal setup for an LSTM model in the task of electrical load forecasting. This configuration comprised 15 neurons, a batch size of 16, and employed the Adamax optimization algorithm. Applying this specific setup yielded a mean squared error (MSE) of 5.584 MW2 and an R2 value of 0.99. High R2 values and low MSE values indicate that the LSTM model accurately captures changes in electricity consumption with minimal deviation between predicted and actual consumption values. Selection of appropriate parameters significantly enhances the performance of the predictive model and resulted in a reduction of the MSE error from 12.706 to 5.584 MW2. The optimized configuration of the LSTM model, tailored through extensive experimentation, enhances its predictive capabilities. The proposed LSTM model holds practical utility for integrating into systems for monitoring and forecasting mode reliability of electrical networks, particularly in the Western energy hub of the Republic of Kazakhstan. Its accuracy and reliability make it valuable for energy resource management and infrastructure planning

Predicting Fine Dead Fuel Load of Forest Floors Based on Image Euler Numbers

The fine dead fuel load on forest floors is the most critical classification feature in fuel description systems, affecting several parameters in the manifestation of wildland fires. An accurate determination of this fine dead fuel load contributes substantially to effective wildland fire prevention, monitoring, and suppression. This study investigated the viability of incorporating image Euler numbers into predictive models of fine dead fuel load via the taking photos method. Pinus massoniana needles and Quercus fabri broad leaves—typical fuel types in karst areas—served as the research subjects. Accurate field data were collected in the Tianhe Mountain forests, China, while artificial fine dead fuelbeds of differing loads were constructed in the laboratory. Images of the artificial fuelbeds were captured and uniformly digitized according to various conversion thresholds. Thereafter, the Euler numbers were extracted, their relationship with fuel load was analyzed, and this relationship was applied to generate three load-prediction models based on stepwise regression, nonlinear fitting, and random forest algorithms. The Euler number had a significant relationship with both P. massoniana and Q. fabri fuel loads. At low conversion thresholds, the Euler number was negatively correlated with fuel load, whereas a positive correlation was recorded when this threshold exceeded a certain value. The random forest model showed the best prediction performance, with mean relative errors of 9.35% and 14.54% for P. massoniana and Q. fabri, respectively. The nonlinear fitting model displayed the next best performance, while the stepwise regression model exhibited the largest error, which was significantly different from that of the random forest model. This study is the first to propose the use of image features to predict the fine fuel load on a surface. The results are more objective, accurate, and time-saving than current fuel load estimates, benefiting fuel load research and the scientific management of wildland fires.

Prediction of Load Demand in Home Area Network Using LSTM

Load forecasting is one of the most important tools for the energy management system in the modern world. Forecasting power consumption and load demand calculation became an interesting topic for the stakeholders in the electricity market. Decision-making in purchasing and generating electric power, load switching, and demand side management are dependent on load forecasting. This research work focuses on the prediction of power consumption in a Home Area Network (HAN) using time series forecasting methods like Long short-term memory (LSTM) neural Networks. Our goal was to design a model that could precisely forecast the electrical load required in a Home Area Network. Utility companies and homeowners can utilize this model to better plan and control their power usage. It can assist in lowering the likelihood of power outages and enhancing the effectiveness of the electrical system. The Root Mean Squared Error (RMSE) is used as the performance measure in our work. The dataset considered is from the UCI repository with 350400 rows and 4 parameters such as active power, and 3 submetering values, to achieve realistic data for training the model used the encoder-decoder LSTM model for load prediction and achieved an RMSE value of 23 and an MAE value of 18.6

Short‐term electric load forecasting based on empirical wavelet transform and temporal convolutional network

AbstractShort‐term load forecasting is the basis of power system operation and analysis and is of great significance for the stable operation of power systems. To solve the problems of insufficient mining of the intrinsic information of load data, randomness, and non‐linearity, and to improve the accuracy of load prediction, the authors propose a short‐term power load prediction model based on empirical wavelet transform (EWT) decomposition and the temporal convolutional network (TCN). First, the Pearson coefficient is used to eliminate the less relevant influencing factors to reduce the complexity of the model. Then, the EWT algorithm is used to decompose the original load signal to fully exploit the load data time domain and frequency domain information, while solving the problems of non‐linearity and randomness. Finally, the decomposed subsequences are input to the TCN network for prediction superposition to obtain the final results. The experimental results show that, compared with the single models TCN, gated recurrent units (GRU), and long short‐term memory (LSTM), and the hybrid models EWT‐GRU, EWT‐LSTM, and VMD‐TCN, the R2 of the short‐term power load forecasting model based on EWT‐TCN is improved by 0.2099%, 0.2519%, 0.3453%, 0.0334%, 0.1766%, and 0.1228%, respectively.

Artificial-intelligence-enabled dynamic demand response system for maximizing the use of renewable electricity in production processes

AbstractThe transition towards renewable electricity provides opportunities for manufacturing companies to save electricity costs through participating in demand response programs. End-to-end implementation of demand response systems focusing on manufacturing power consumers is still challenging due to multiple stakeholders and subsystems that generate a heterogeneous and large amount of data. This work develops an approach utilizing artificial intelligence for a demand response system that optimizes industrial consumers’ and prosumers’ production-related electricity costs according to time-variable electricity tariffs. It also proposes a semantic middleware architecture that utilizes an ontology as the semantic integration model for handling heterogeneous data models between the system’s modules. This paper reports on developing and evaluating multiple machine learning models for power generation forecasting and load prediction, and also mixed-integer linear programming as well as reinforcement learning for production optimization considering dynamic electricity pricing represented as Green Electricity Index (GEI). The experiments show that the hybrid auto-regressive long-short-term-memory model performs best for solar and convolutional neural networks for wind power generation forecasting. Random forest, k-nearest neighbors, ridge, and gradient-boosting regression models perform best in load prediction in the considered use cases. Furthermore, this research found that the reinforcement-learning-based approach can provide generic and scalable solutions for complex and dynamic production environments. Additionally, this paper presents the validation of the developed system in the German industrial environment, involving a utility company and two small to medium-sized manufacturing companies. It shows that the developed system benefits the manufacturing company that implements fine-grained process scheduling most due to its flexible rescheduling capacities.

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.

Load Forecasting and Operation Optimization of Ice-Storage Air Conditioners Based on Improved Deep-Belief Network

The prediction of cold load in ice-storage air conditioning systems plays a pivotal role in optimizing air conditioning operations, significantly contributing to the equilibrium of regional electricity supply and demand, mitigating power grid stress, and curtailing energy consumption in power grids. Addressing the issues of minimal correlation between input and output data and the suboptimal prediction accuracy inherent in traditional deep-belief neural-network models, this study introduces an enhanced deep-belief neural-network combination prediction model. This model is refined through an advanced genetic algorithm in conjunction with the “Statistical Products and Services Solution” version 25.0 software, aiming to augment the precision of ice-storage air conditioning load predictions. Initially, the input data undergo processing via the “Statistical Products and Services Solution” software, which facilitates the exclusion of samples exhibiting low coupling. Subsequently, the improved genetic algorithm implements adaptive adjustments to surmount the challenge of random weight parameter initialization prevalent in traditional deep-belief networks. Consequently, an optimized deep-belief neural-network load prediction model, predicated on the enhanced genetic algorithm, is established and subjected to training. Ultimately, the model undergoes simulation validation across three critical dimensions: operational performance, prediction evaluation indices, and operating costs of ice-storage air conditioners. The results indicate that, compared to existing methods for predicting the cooling load of ice-storage air conditioning, the proposed model achieves a prediction accuracy of 96.52%. It also shows an average improvement of 14.12% in computational performance and a 14.32% reduction in model energy consumption. The prediction outcomes align with the actual cooling-load variation patterns. Furthermore, the daily operational cost of ice-storage air conditioning, derived from the predicted cooling-load data, has an error margin of only 2.36%. This contributes to the optimization of ice-storage air conditioning operations.

A fusion gas load prediction model with three-way residual error amendment

Accurately predicting gas load is crucial for optimal planning and scheduling of natural gas production. Existing machine learning or deep learning-based prediction methods primarily aim to improve accuracy. However, these methods face challenges such as overlapped features, significant background noise, and residual errors. In response to these challenges, we proposed a fusion prediction model, known as the Double Temporal Convolutional Network (TCN) and Light Gradient Boosting Machine (LightGBM) with Three-way Residual Error Amendment (DT-LGBM-3WREA). To address the overlapped feature issue in time series data, we utilize the STL module for data decomposition. To handle background noise, the network incorporates a double TCN module specifically designed for trend and seasonal components. Thus, it can better avoid the transmission of noise between modules. To address residual error, we introduce three-way decision methodology and develop the 3WREA module, which aims to avoid local optima and random factors from perturbing the prediction accuracy. This approach mitigates the influence of remainder item on overall prediction performance. Experimental results demonstrate that the DT-LGBM-3WREA model excels in gas load prediction scenarios, surpassing state-of-the-art methods.

Hybrid Elastic Scaling Strategy for Container Cloud based on Load Prediction and Reinforcement Learning

To harness the advantages of both proactive and responsive scaling, adapting to various workload scenarios, this paper introduces a container hybrid scaling strategy called HyPredRL, rooted in load prediction and reinforcement learning. Within the proactive scaling module RL-PM, a load prediction model, MSC-LSTM, predict workloads and, in conjunction with current workload states, leverages reinforcement learning agents for intelligent scaling decisions. The responsive scaling strategy, SLA-HPA, enhances Kubernetes’ native scaling strategy, which primarily considers resource utilization, by incorporating response time metrics. Ultimately, a hybrid scaling controller is designed, applying the principles of “rapid scaling out” and “balanced conflicts” to coordinate proactive and responsive scaling. Experimental results demonstrate that HyPredRL outperforms existing methods in SLA violation rate, resource utilization, and request response time, effectively improving application performance and scalability.

Short-term PV power prediction study based on FCM-BiGRU

Addressing the issue of large prediction error in short-term load prediction of existing neural network models, this study proposes a short-term load forecasting approach that combines fuzzy C-mean clustering and a two-way gated recurrent neural network model. Fuzzy C-mean clustering is first applied to cluster the original data into three typical days, and the grouped data are trained using a bidirectional gated recurrent neural network model for load prediction. The conclusive experiment demonstrates that the proposed approach introduced in this study exhibits a high prediction accuracy in the context of short-term photovoltaic output forecasting, and there is also a substantial error reduction compared with the existing neural network methods.

Hybrid load prediction model of 5G base station based on time series decomposition and GRU network with parameter optimization

AbstractTo ensure the safe and stable operation of 5G base stations, it is essential to accurately predict their power load. However, current short‐term prediction methods are rarely applied rationally in pertinent circumstances to the features of base station power load over time. For high accuracy and generalization capabilities, this work proposes a hybrid approach that combines gated recurrent unit (GRU) with particle swarm optimization (PSO) and completes ensemble empirical mode decomposition with adaptive noise (CEEMDAN). The complex load is decomposed into multiple components to improve the fit of the neural network. To deal with the nonlinearity that constrains the modal aliasing and data noise, CEEMDAN is used to reconstruct the trend and noise sequences. The GRU network is utilized to improve the neural network fitness and obtain long‐term features. In addition, PSO is used to optimize the number of neurons and the learning rate of the GRU. Compared with existing neural network GRUs, the RMSE is reduced by 16.6, the mean absolute error is reduced by 11.97, and the coefficient of R2 is improved by 0.13, indicating that the model has a better fitting effect. The comparisons prove that the proposed model has better accuracy than the existing methods.