Smart Grid Load Research Articles

Adaptive Single-layer Aggregation Framework for Energy-efficient and Privacy-preserving Load Forecasting in Heterogeneous Federated Smart Grids

Federated Learning (FL) enhances predictive accuracy in load forecasting by integrating data from distributed load networks while ensuring data privacy. However, the heterogeneous nature of smart grid load forecasting introduces significant challenges that current methods struggle to address, particularly for resource-constrained devices due to high computational and communication demands. To overcome these challenges, we propose a novel Adaptive Single Layer Aggregation (ASLA) framework tailored for resource-constrained smart grid networks. The ASLA framework mitigates data heterogeneity issues by focusing on local learning and incorporating partial updates from local devices for model aggregation in adaptive manner. It is optimized for resource-constrained environments through the implementation of a stopping criterion during model training and weight quantization. Our evaluation on two distinct datasets demonstrates that quantization results in a minimal loss function degradation of 0.01% for Data 1 and 1.25% for Data 2. Furthermore, local model layer optimization for aggregation achieves substantial communication cost reductions of 829.2-fold for Data 1 and 5522-fold for Data 2. The use of an 8-bit fixed-point representation for neural network weights leads to a 75% reduction in storage/memory requirements and decreases computational costs by replacing complex floating-point units with simpler fixed-point units. By addressing data heterogeneity and reducing storage, computation, and communication overheads, the ASLA framework is well-suited for deployment in resource-constrained smart grid networks.

Enhancing smart grid load forecasting: An attention-based deep learning model integrated with federated learning and XAI for security and interpretability

Smart grid is a transformative advancement that modernized the traditional power system for effective electricity management, and involves optimized energy distribution by load forecasting. Precise load forecasting provides the best utilization of energy resources and increases sustainability. Dynamic changes of several connected factors, such as temporal and geographical variability, pose challenges to accurate load prediction. Integrating Artificial Intelligence (AI) in the smart grid can enhance the performance of the forecasting process by capturing these changes. This study investigated load forecasting tasks on four different datasets. Several preprocessing and augmentation techniques are applied to increase the data quality. An attention-based 1D-CNN-GRU model is proposed to capture the temporal patterns from the time-series data, and the hyperparameters of the model are optimized using a particle swarm optimization (PSO) algorithm that also accelerates the convergence and results in an efficient training session. Empirical evaluations highlight that the proposed model substantially minimizes the loss, reflecting the ability to make accurate predictions. It obtains MAE values of 0.12, 0.8, 16.48, and 82.64 for the four datasets. Moreover, the explainable AI (XAI) technique is applied using Shapley Additive explanations (SHAP) to interpret the model prediction, providing the feature ranking based on their prediction score. Moreover, this study utilizes federated learning, enables collaborative training, maintains the privacy of the grid data, and secures the process comprehensively. The aggregation mechanism in federated learning is modified using pruning-based methods that reduce the parameters and computational cost, resulting in a more efficient framework. Integrating all these approaches provides valuable insights for developing a load forecasting model and outlines potential contributions in the smart grid domain.

Coordinating electric vehicle charging with multiagent deep Q-networks for smart grid load balancing

Integrating EVs (Electric Vehicles) with the electrical system presents essential load distribution difficulties because EV recharging structures are unpredictable and variable. The article presents an innovative technique employing multiple-agent deeper Q-Networking (MADQN) to coordinate electric automobiles and improve the electricity system balance of load. The suggested MADQN simulation rapidly optimizes battery charge plans by utilizing the capabilities of multiple agent networks as well as deeper reinforced learning. The framework adjusts to current network situations utilizing cooperative decision-making between substances, considering variables like a need for power, accessibility to green energy sources, and protection of the arrangement. Beneficial load distribution is made possible when reducing expenses and ecological damage because of the system's capacity to gather data from and modify intricate, changing circumstances. The findings from the modelling indicate how well the suggested MADQN method works to enhance network efficiency, lower peak usage, and use more sustainable power resources. These factors help build a more robust, adaptable, intelligent grid environment.

Optimization and research of smart grid load forecasting model based on deep learning

Abstract In order to accurately grasp the power consumption of the market and deeply understand the operation law of the power market, the power grid must achieve accurate power load prediction by studying the supply and demand of the power system and the change law. Therefore, a smart grid load prediction analysis method based on deep learning is proposed. Firstly, DenseNet network is used to extract features, so as to achieve feature reuse and improve efficiency. Then, combining the long short-term memory (LSTM) network based on attention mechanism, a combined model DenseNet–AM–LSTM is proposed to solve the long-term dependence problem of feature extraction. After using batch normalization, the model can use higher learning rate to improve the training speed of the model and obtain the best prediction accuracy of the model. The experimental results show that this method can accurately predict the power load, and the accuracy is higher than the current popular methods, and it is expected to become an important technical support for solving the core problems of smart grid.

Demand side management using a novel archimedes optimization algorithm in a smart grid environment

Demand side management (DSM) is a smart grid technology that enables consumers to make decisions about their energy use, lowers energy suppliers’ peak hour demand, and changes the load profile. Demand Side Management (DSM) is regarded as the most significant method used in a Smart Grid (SG), as it helps consumers produce accurate information about their electrical energy usage and assists the utility in reducing peak load demand and reshaping the demand curve. By effectively utilising storage with Renewable Energy Systems (RES), DSM seeks to reduce peak demand, electricity costs, and emission rates. In this paper, we have proposed a load-shifting method for the DSM with a large number of controllable devices. The load-shifting issue has been handled hourly, throughout the course of a 24-hour day, in order to reduce the peak demand, lower the power cost, and minimise the Peak to Average load Ratio (PAR). The Archimedes Optimization (AO) method has been utilised in residential loads in SG to achieve the goal of load shifting by minimising of the problem to the DSM. The simulation findings demonstrate that the suggested demand side management technique generates significant cost savings while lowering the smart grid’s peak load demand.

Improved reinforcement learning-based real-time energy scheduling for prosumer with elastic loads in smart grid

In this study, we investigate the dynamic energy-scheduling problem of a prosumer (producer/consumer) with an energy storage device (EDS) and elastic loads. The goal is to develop efficient real-time scheduling strategies for prosumers, and to minimise their total long-term costs (i.e. cost of energy purchased from the external grid and depreciation cost of the EDS). The challenges are twofold: the uncertainty of the energy output of the prosumer and the time-coupling constraints of the EDS and elastic loads. To address these challenges, we first describe the dynamic energy-scheduling problem as a Markov decision process. Then, an approximate state dual-agent Q-learning algorithm is proposed to solve the optimal dynamic scheduling problem by improving the model-free reinforcement learning(RL) method. Compared with the traditional RL method, the proposed algorithm reduces the system-state dimensions and exhibits improved performance. The proposed algorithm can only be assisted by mutual interactions between the environment with a reward feedback mechanism to dynamically respond to uncertain changes in the environments, without modelling or predicting the system environments. Finally, extensive empirical evaluations using real-world traces are conducted to study the effectiveness of the proposed algorithm. The results show that the proposed algorithm can reduce the total cost of the prosumer by up to 6.3%, 11.7% and 22.4% compared with the traditional RL method, Lyapunov optimisation and greedy algorithm, respectively.

Construction of a smart grid load forecasting platform based on clustering algorithm

Abstract With the rapid development of economic levels, the demand for electricity usage in various industrial sectors has continued to rise. In order to adequately meet the growth in demand for electricity usage at each user end within the power system, accurate forecasting of electricity load is required. This paper uses the K-Means algorithm as the basis, combined with the Canopy algorithm, whose simple and efficient advantages can be used as the initial clustering step for demanding clustering algorithms. The PCA algorithm is used to reduce the dimensionality of the residential multidimensional electricity consumption feature set, and after optimization, the feature vector weights are calculated to obtain the appropriate selection to determine the training and testing samples. The improved K-Means algorithm carries out five clustering tests, and its average accuracy is above 97%. The average relative error is then used as an indicator to compare the algorithm with the time series method, curve extrapolation method, and WKNR method for analysis. The average relative error of the smart grid load forecasting method proposed in this paper is 0.87%, while the average relative errors of the other three algorithms are 1.64%, 1.57%, and 0.93%, respectively. The distribution of relative errors falls less than 1% more than the other methods. It can be seen that the improved K-Means algorithm has higher prediction accuracy and also makes the smart grid load testing platform more practical due to its simple implementation principle.

Cloud-Edge Collaborative Scheduling with a Focus on Clean Energy

With the promotion of the national "double carbon" goal, the power system is developing towards the direction of low-carbon transformation. In order to achieve the goal of "striving to peak carbon dioxide emissions by 2030 and striving to achieve carbon neutrality by 2060", we must actively promote the consumption of a high proportion of renewable energy from the grid, which is the most urgent issue to be addressed. In this chapter, access to clean energy will involve multiple aspects such as source, network, load and storage. However, due to the intermittent, random and volatile nature of wind power and photovoltaic power generation, the challenges faced by significant users of the power system are enormous. Traditional energy Internet dispatching adopts centralized dispatching. In this paper, by deploying edge nodes, the autonomous decision-making and autonomous collaboration of power grid nodes at all levels are enhanced, and the collaborative integration level of source, network, load and storage of smart power grid is improved. Aimed at the current power supply and demand imbalance, new energy access problems and energy storage problems. In this paper, a service adaptation algorithm based on dynamic priority is proposed based on the scenario of load storage integration of source network under renewable energy access. Experimental results show that, compared with other algorithms, this algorithm has lower scheduling time and execution time and better performance under the condition of ensuring the highest clean energy consumption rate and first-order load priority response.

Demand response method considering multiple types of flexible loads in industrial parks

With the rapid development of the energy internet, the proportion of flexible loads in smart grid is getting much higher than before. It is highly important to model flexible loads based on demand response. Therefore, a new demand response method considering multiple flexible loads is proposed in this paper to character the integrated demand response (IDR) resources. Firstly, a physical process analytical deduction (PPAD) model is proposed to improve the classification of flexible loads in industrial parks. Scenario generation, data point augmentation, and smooth curves under various operating conditions are considered to enhance the applicability of the model. Secondly, in view of the strong volatility and poor modeling effect of Wasserstein-generative adversarial networks (WGAN), an improved WGAN-gradient penalty (IWGAN-GP) model is developed to get a faster convergence speed than traditional WGAN and generate higher quality samples. Finally, the PPAD and IWGAN-GP models are jointly implemented to reveal the degree of correlation between flexible loads. Meanwhile, an intelligent offline database is built to deal with the impact of nonlinear factors in different response scenarios. Compared with Fourier, SVM, and BP-NET, the root mean square error is reduced by 2.854MW, 3.576MW, and 3.507MW, respectively. The relative error of the amount of unresponsiveness has been reduced significantly by over 25% compared to the traditional methods. Numerical examples have been performed with the results proving that the proposed method is significantly better than the existing technologies in reducing load modeling deviation and improving the responsiveness of park loads.

Demand Response for Optimal Power Usage Scheduling Considering Time and Power Flexibility of Load in Smart Grid

Demand response (DR) shaves peak energy consumption and drives energy conservation to ensure reliable operation of power grid.With the emergence of the smart power grid (SPG), DR has become increasingly popular and highly contributes to energy optimization. On this note, in this work, DR is adopted for scheduling home appliances to reduce utility bill payment, peak to average demand ratio (PADR), and discomfort. First, home appliances are classified into two categories according to time and power flexibility: time-flexible and power-flexible. Secondly, the demand-side users power usage scheduling problem is modelled as per the user priority and modes of operation considering demand and supply. Finally, the energy consumption scheduler (ECS) is developed to adjust the time and power of both types of appliances under different operation modes to acquire desired tradeoff between utility bills payment and discomfort, and PADR and discomfort. Simulation results depict that employing the proposed ECS benefits demand-side users by minimizing their utility bills payment, PADR, and achieving the desired tradeoff between utility bill payment and discomfort, and PADR and discomfort. Results illustrate that developed reduced utility bill payment and alleviated PADR without compromising comfort by 28% and 21%, respectively, compared to without scheduling case.

A Framework to Predict Variability Characteristics in Building Load Profiles

The expansion of Advanced Metering Infrastructure (AMI) has provided building operators and researchers detailed information on building energy consumption. The majority of AMI systems, however, record data at relatively low resolutions of 15, 30, or 60 minutes, due to cost, storage and bandwidth limitations. Emerging applications in power flow analysis, Quasi-Static Time-Series Simulation (QSTS), smart grid integration and load matching, however, require data at higher resolutions. Short-term energy demand can deviate significantly from long-term averages, with an unknown magnitude and frequency when only low-resolution load profile data is available. This paper presents a novel data-driven approach to predict characteristics of the missing high-resolution information in a low-resolution signal, applicable to both measured and modeled building load profile data, utilizing machine learning regression algorithms. In the proposed framework, the relationship between characteristics of high-resolution and low-resolution signals is learned from the decomposition and characterization of a subset of high-resolution building data. This paper validates the underlying hypotheses and methodology of this approach through a single-building case study, training a variety of machine learning models on one year of data, and using the resulting models to predict high-resolution characteristics in a different year. An Ensemble Tree regression model demonstrates a high predictive accuracy (R2 of 0.79-0.92) for several statistical metrics of the high-resolution load profile. These results support the broader potential for leveraging low-resolution information to accurately constrain predictions of missing high-resolution information in building load profiles, which may greatly increase the utility of both measured and modeled data in many practical and research applications. Generalizing such models will require analysis of high-resolution data from a diverse set of building types.

An exposition on the prediction of load on a Smart Grid

Smart grids depend on AI-based load forecasting to estimate future power demand (AI). Deep learning is especially important in smart grid load forecasting with neural networks (ANN). Processing time and data are needed to count smart grid deep learning. Combining data would speed load projections. The bottleneck strategy has been abandoned to attain this precision. Keeping the lights on requires short-term electricity demand prediction. But, the load’s intricacy and volatility make it fun to predict. EEMD breaks the load into many frequency-dependent components of different strengths. MLR predicts low-frequency regularities, while LSTM neural networks predict high-frequency components. Computational extent is unchanged. Despite its varied aggregation scope, the electric grid’s large data can be used to create the most effective deep learning models for Short-term Load Forecasting (STLF) in electrical networks. Hence, a suitable forecasting strategy uses deep learning with a Micro-clustering (MC) job that mixes unsupervised and supervised clustering tasks utilizingKmeans and Gaussian Support Vector Machine. To guarantee accuracy. B-bidirectional LSTMs can store feed-forward and future hidden-layer data. Feedback and feed-forward loops do this. The DaviesBouldering index determined cluster production per hour. MC with B-LSTM networks improves prediction,especially around spike locations. Forecasting RE generation and grid load is difficult. Prosumer microgrids (PMGs) sell electricity to aggregators. A hybrid machine learning-based load and weather data transmission method provides the biggest benefit. ANFIS, MLP, and radial basis function artificial neural networks (ANNs) would be used in this technique (RBF). Machine learning-based hybrid forecasting can improve accuracy.

Relocating of PHEVs Peak Load in Smart Grid Using Wind Power Output and Real Time Pricing as Objective Function

Relocating of PHEVs Peak Load in Smart Grid Using Wind Power Output and Real Time Pricing as Objective Function

Hybrid Deep Learning Applied on Saudi Smart Grids for Short-Term Load Forecasting

Despite advancements in smart grid (SG) technology, effective load forecasting utilizing big data or large-scale datasets remains a complex task for energy management, planning, and control. The Saudi SGs, in alignment with the Saudi Vision 2030, have been envisioned as future electrical grids with a bidirectional flow of power and data. To that end, data analysis and predictive models can enhance Saudi SG planning and control via artificial intelligence (AI). Recently, many AI methods including deep learning (DL) algorithms for SG applications have been published in the literature and have shown superior time series predictions compared with conventional prediction models. Current load-prediction research for the Saudi grid focuses on identifying anticipated loads and consumptions, on utilizing limited historical data and the behavior of the load’s consumption, and on conducting shallow forecasting models. However, little scientific proof on complex DL models or real-life application has been conducted by researchers; few articles have studied sophisticated large-scale prediction models for Saudi grids. This paper proposes hybrid DL methods to enhance the outcomes in Saudi SG load forecasting, to improve problem-relevant features, and to accurately predict complicated power consumption, with the goal of developing reliable forecasting models and of obtaining knowledge of the relationships between the various features and attributes in the Saudi SGs. The model in this paper utilizes a real dataset from the Jeddah and Medinah grids in Saudi Arabia for a full year, 2021, with a one-hour time resolution. A benchmark strategy using different conventional DL methods including artificial neural network, recurrent neural network (RNN), conventional neural networks (CNN), long short-term memory (LSTM), gated recurrent unit (GRU), and different real datasets is used to verify the proposed models. The prediction results demonstrate the effectiveness of the proposed hybrid DL models, with CNN–GRU and CNN–RNN with NRMSE obtaining 1.4673% and 1.222% improvements, respectively, in load forecasting accuracy.

Robust Integration of Electric Vehicles Charging Load in Smart Grid’s Capacity Expansion Planning

Robust Integration of Electric Vehicles Charging Load in Smart Grid’s Capacity Expansion Planning

Learning customer behaviour for effective load forecasting

Cloud computing is quickly expanding, and there are an increasing number of cloud providers. To stay competitive while earning a profit, cloud providers must focus on cost efficiency and resource cost maximization. The profit maximization challenge in federated cloud systems has been investigated in order to maximize the degree of multiplexing. Outline unique economics-inspired resource allocation strategies to address the profit maximization challenge from the standpoint of a purely active cloud provider. Admission control strategies have been presented that are adjusted within a profit management framework to maximize resource cost. Existing abstractions for in-memory storage on clusters, including as distributed shared memory, key value stores, databases, and Piccolo, use fine-grained modifications to mutable state as their interface. It has been fine-tuned to anticipate cluster load. Summing the loads of each cluster yields the total load for the entire grid. He suggested Smart Grid load forecasting approach has two primary benefits. Learning consumer habits enhances forecast accuracy while also being computationally efficient. SCCRF can simulate a single customer's load forecasting problem while concurrently selecting important features to determine its energy consumption trend. Experiments conducted from various angles show the benefits of the suggested load forecasting system.

Construction of Smart Grid Load Forecast Model by Edge Computing

This research aims to minimize the unnecessary resource consumption by intelligent Power Grid Systems (PGSs). Edge Computing (EC) technology is used to forecast PGS load and optimize the PGS load forecasting model. Following a literature review of EC and Internet of Things (IoT)-native edge devices, an intelligent PGS-oriented Resource Management Scheme (RMS) and PGS load forecasting model are proposed based on task offloading. Simultaneously, an online delay-aware power Resource Allocation Algorithm (RAA) is developed for EC architecture. Finally, comparing three algorithms corroborate that the system overhead decreases significantly with the model iteration. From the 40th iteration, the system overhead stabilizes. Moreover, given no more than 50 users, the average user delay of the proposed delay-aware power RAA is less than 13 s. The average delay of the proposed algorithm is better than that of the other two algorithms. This research contributes to optimizing intelligent PGS in smart cities and improving power transmission efficiency.

A Bottom-up model for simulating residential harmonic injections

The use of modern loads in residential distribution networks has given rise to increasing concern and to the need for techniques that improve the understanding of their collective impact. To address this issue, this paper presents a simulation tool that models the stochastic profiles of harmonic currents injected by residential loads in modern smart grids. The simulator considers a bottom-up approach by taking into account the stochastic consumption patterns of each household device, and their harmonic injection spectra, modeled with Gaussian mixtures. In the presented tool, weekly harmonic injection profiles can be generated for a single dwelling or several dwellings. The model was validated by means of weekly current injection measurements performed in seventeen dwellings. The presented harmonic injection model named Reshapes (Residential Harmonic Probabilistic Emission Simulator) has been made freely available for researchers so that they can use it for their own purposes.

Demand Response Method Considering Multiple Types of Flexible Loads in Industrial Parks

With the rapid development of the energy internet, the proportion of flexible loads in smart grid is getting much higher than before. It is highly important to model flexible loads based on demand response. Therefore, a new demand response method considering multiple flexible loads is proposed in this paper to character the integrated demand response (IDR) resources. Firstly, a physical process analytical deduction (PPAD) model is proposed to improve the classification of flexible loads in industrial parks. Scenario generation, data point augmentation, and smooth curves under various operating conditions are considered to enhance the applicability of the model. Secondly, in view of the strong volatility and poor modeling effect of Wasserstein-generative adversarial networks (WGAN), an improved WGAN-gradient penalty (IWGAN-GP) model is developed to get a faster convergence speed than traditional WGAN and generate a higher quality samples. Finally, the PPAD and IWGAN-GP models are jointly implemented to reveal the degree of correlation between flexible loads. Meanwhile, an intelligent offline database is built to deal with the impact of nonlinear factors in different response scenarios. Numerical examples have been performed with the results proving that the proposed method is significantly better than the existing technologies in reducing load modeling deviation and improving the responsiveness of park loads.

Short-Term Load Forecasting Method Based on Deep Reinforcement Learning for Smart Grid

Short-term load forecasting is an important part to support the planning and operation of power grid, but the current load forecasting methods have the problem of poor adaptive ability of model parameters, which are difficult to ensure the demand for efficient and accurate power grid load forecasting. To solve this problem, a short-term load forecasting method for smart grid is proposed based on multilayer network model. This method uses the integrated empirical mode decomposition (IEMD) method to realize the orderly and reliable load state data and provides high-quality data support for the prediction network model. The enhanced network inception module is used to adaptively adjust the parameters of the deep neural network (DNN) prediction model to improve the fitting and tracking ability of the prediction network. At the same time, the introduction of hybrid particle swarm optimization algorithm further enhances the dynamic optimization ability of deep reinforcement learning model parameters and can realize the accurate prediction of short-term load of smart grid. The simulation results show that the mean absolute percentage error e MAPE and root-mean-square error e RMSE of the performance indexes of the prediction model are 10.01% and 2.156 MW, respectively, showing excellent curve fitting ability and load forecasting ability.