Search

Renewable energy sources (RES) are increasingly being developed and used to address the energy crisis and protect the environment. However, the large‐scale integration of wind and solar energy into the power grid is still challenging and limits the adoption of these new energy sources. Microgrids (MGs) are small‐scale power generation and distribution systems that can effectively integrate renewable energy, electric loads, and energy storage systems (ESS). By using MGs, it is possible to consume renewable energy locally and reduce energy losses from long‐distance transmission. This paper proposes a deep reinforcement learning (DRL)‐based energy management system (EMS) called DRL‐MG to process and schedule energy purchase requests from customers in real‐time. Specifically, the aim of this paper is to enhance the quality of service (QoS) for customers and reduce their electricity costs by proposing an approach that utilizes a Deep Q‐learning Network (DQN) model. The experimental results indicate that the proposed method outperforms commonly used real‐time scheduling methods significantly. [ABSTRACT FROM AUTHOR]

In order to solve the collaborative optimization scheduling of multi‐microgrid under the high penetration rate of new energy, this paper considered the energy interaction between micro‐grids in multi‐microgrid and the relationship between new energy consumption and electricity cost, constructed a collaborative scheduling model considering both micro‐grid load and main grid wind and optical energy storage, proposed objective function based on economic cost, and improved Genetic Algorithm (GA). The elite thought and catastrophe thought are used to optimize the selection operation, and the particle swarm optimization algorithm is used to optimize the mutation operation. Furthermore, three scenarios were selected to verify the effectiveness of the proposed model and the improved GA. The results show that the proposed model can ensure the stable operation of the multi‐microgrid system with a high proportion of new energy access and reduce the operation cost. In addition. the improved algorithm solves the problems of easy to fall into local optimum and slow iteration speed, and has better performance in solving the model. [ABSTRACT FROM AUTHOR]

With the continuous growth of electricity demand, the safe and stable operation of distribution lines is crucial for power transportation. Unmanned aerial vehicle (UAV) inspection has been widely used for the maintenance and repair of distribution lines. Due to the limitations of computational power and endurance, it is difficult for UAVs to independently complete data processing. Combined with mobile edge computing (MEC), this paper proposes a computing offloading strategy based on multi‐agent reinforcement learning and double‐layer offloading mechanism, which can further utilize the computing power of non‐task devices and edge servers. Firstly, three‐layer system architecture, named MEC‐U‐NTDC (MEC‐UAV‐Non‐task Device Cloud), is built. Secondly, double‐layer offloading mechanism is designed to comprehensively utilize the computing power of edge servers and neighbouring non‐task devices. Finally, a multi‐agent algorithm DLMQMIX is proposed to minimize the total cost for UAV inspection. Simulation experiments show that the proposed algorithm can effectively solve the task offloading problem of UAV‐aided distribution line inspection, and compared with algorithms such as PSO, GA, and QMIX, it performs better in terms of average delay, system cost, and load balancing, achieving a smaller total system cost. [ABSTRACT FROM AUTHOR]

The UK net‐zero target requires the integration of significant renewable energy resources into the electrical grid. This, together with the projected growth in electricity demand imposes practical challenges on the power transfer capability of existing transmission feeders. For environmental and planning reasons, construction of new overhead lines is problematic, and where possible upgrading of existing substations and lines is preferred. This paper investigates the feasibility of transforming an existing three‐phase (3Φ) double‐circuit 400 kV line into a six‐phase (6Φ) feeder for a simulated future GB scenario. Results indicate a 6Φ feeder, operating at a 'phase‐adjacent phase' voltage of 400 kV can effectively solve the constraints of boundaries in transmission networks. When considering the various operating contingencies, associated with an important UK network boundary and its expected near‐future winter‐peak power transfer requirements, the thermal overload issues are mitigated by transforming a feeder from 3Φ to 6Φ. The paper demonstrates upgrading to 6Φ technology is a potential solution to certain future boundary constraints and in these cases avoids the need to build new underground or overhead AC/DC lines. [ABSTRACT FROM AUTHOR]

This paper proposes a situational awareness‐based method of load control for safe electricity consumption by industrial users to assess the risk of regulated load equipment within industrial users and to ensure their safe use of electricity. Firstly, in the situational perception stage, collecting key parameters such as controllable equipment within industrial users, and constructing a risk indicator system for industrial users in the process of load control from four perspectives: the degree of controllability of load equipment, the correlation and mutual influence of load equipment, the uncertainty of self‐provided power and economic losses; Then, in the situational understanding and presentation stage, a risk assessment method that integrates a self‐learning weight model and a cloud model is proposed to analyze the risk of industrial users under control; Finally, in the situational guidance stage, based on the assessment results of the risk situational of industrial users, industrial users' safe electricity consumption is controlled in multiple rounds to achieve the objective of maintaining safe and reliable operation of the power grid by accepting control at a low‐risk level. The simulation of the industrial users of steel mills is used to verify the rationality and effectiveness of the method proposed here. [ABSTRACT FROM AUTHOR]

In Latin America, distribution networks are mostly radial, with high energy losses, representing about 16% of the region's electricity consumption. In Cuba, one of the alternatives that has been proposed to reduce these losses is the distribution of photovoltaic (PV) power plants of up to 3 MWp in them. This paper presents a new hybrid optimization algorithm to localize and size PV power plants to minimize energy losses in radial distribution networks. The method localizes the power plants using Empirical Discrete Metaheuristic in conjunction with a novel strategy that reduces the execution time of the algorithm. The sizes are found using the Coordinate Search Method, which performs one‐dimensional searches in the directions of the variables of the objective function. The algorithm was run on a 33‐bus IEEE test system in which up to five power plants were optimally installed, taking into account load variations at the distribution level and changes in the weather conditions under which the power plants operate. It should be noted that the execution times for each scenario did not exceed 30 s. The algorithm was validated by comparing it with other methods found in the literature and proved to be more efficient than them. [ABSTRACT FROM AUTHOR]

This paper determines the optimal capacity of solar photovoltaic (PV) and battery energy storage (BES) for a grid‐connected house based on an energy‐sharing mechanism. The grid‐connected house, also mentioned as house 1 where it is relevant, shares electricity with house 2 under a mutually agreed fixed energy price. The objective is to minimize the cost of electricity (COE) for house 1 while decreasing the electricity cost of house 2. Practical factors such as real data for solar insolation, electricity consumption, grid constraint, ambient temperature, electricity rate, and battery degradation are considered based on actual data. The developed methodology is examined by taking the actual load data of two houses in South Australia. Different scenarios of contract years between the houses are investigated to make it more practical in real life. Sensitivity analyses are conducted for the sharing of energy between the houses and by changing parameters like export power limitation, load of houses, and costs of PV and BES. Likewise, operational analysis is done for two days of summer and winter. It is found that when energy sharing is applied, the optimal design of the PV‐BES system will achieve lower COE for both houses. [ABSTRACT FROM AUTHOR]

This paper deals with the real‐time optimal operation of active distribution networks (ADNs) hosting hybrid hydrogen‐electricity refuelling stations by benefiting from renewable energy sources (RESs), conversion facilities, and energy storage systems. The hybrid refuelling stations, which are controlled by ADN operator, supply electricity and hydrogen for electric vehicles (EVs) and hydrogen vehicles (HVs), respectively. In addition, the deployment of water equipment technologies in the ADNs, is considered by utilizing water well pumps in the hybrid stations to serve water demand. The principal aim is to minimize the expected operation cost, including the cost of purchasing power from the upstream grid and maintenance and operation costs of each hybrid refuelling station. Various technical and physical constraints are considered to ensure the reliable operation and realistic scheduling of ADNs in the presence of hybrid refuelling stations. This study employs a hybrid information gap decision theory (IGDT)‐stochastic approach to address the uncertain behaviour of wholesale market price, electricity demand of EVs in refuelling stations, RESs output power and nodal demand of ADN to reach a risk‐averse strategy. The developed approach is coded under GAMS software and the effectiveness of the approach is validated by testing on the modified IEEE 33‐bus test system. [ABSTRACT FROM AUTHOR]

Load demand forecasting is very important for the management, designing and analysis of an electrical grid system. Load forecasting has progressively become a crucial component of the energy management system with the growth of the smart micro grid. This study presents a new framework to long term load forecasting in the world of electricity power with the help of historical load trends. The main objective of this research work is estimating monthly electricity demand of an Indian state Chhattisgarh, in terms of per day average load demand using a machine learning model—Long Short‐Term Memory (LSTM). This framework considers average of each day load demand for every month of years 2018–2022 and forecasted per day average load demand for each month of the year 2023. Furthermore, the predicting accuracy is evaluated for training and testing phase, in terms of error metrics like Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE). The MAPE values under the training and testing phase are in the range of 0.010%–0.652% and 0.378%–10.54%, respectively. A comparative study of LSTM model with Artificial Neural Network (ANN) model indicates the proposed LSTM model is more accurate and can be applied for real time load demand forecasting. [ABSTRACT FROM AUTHOR]

Energy forecasting plays a vital role in mitigating challenges in data rich smart grid (SG) systems involving various applications such as demand‐side management, load shedding, and optimum dispatch. Managing efficient forecasting while ensuring the least possible prediction error is one of the main challenges posed in the grid today, considering the uncertainty in SG data. This paper presents a comprehensive and application‐oriented review of state‐of‐the‐art forecasting methods for SG systems along with recent developments in probabilistic deep learning (PDL). Traditional point forecasting methods including statistical, machine learning (ML), and deep learning (DL) are extensively investigated in terms of their applicability to energy forecasting. In addition, the significance of hybrid and data pre‐processing techniques to support forecasting performance is also studied. A comparative case study using the Victorian electricity consumption in Australia and American electric power (AEP) datasets is conducted to analyze the performance of deterministic and probabilistic forecasting methods. The analysis demonstrates higher efficacy of DL methods with appropriate hyper‐parameter tuning when sample sizes are larger and involve nonlinear patterns. Furthermore, PDL methods are found to achieve at least 60% lower prediction errors in comparison to other benchmark DL methods. However, the execution time increases significantly for PDL methods due to large sample space and a tradeoff between computational performance and forecasting accuracy needs to be maintained. [ABSTRACT FROM AUTHOR]

Non‐intrusive load monitoring (NILM) is an important technology for deeply mining consumers' internal electricity consumption information, which can improve the level of awareness of the load and significantly improve the demand‐side management capability of the smart grid. For a long time, traditional NILM faces the challenge of huge data, long training time and low accuracy. To address this issue, this paper proposes an adaptative lightweight seq2subseq model. The model adaptively determines the optimum window length of the active power segment to extract the appliance characteristics and thus reduces the redundant data to construct the appliance‐level‐seq2subseq model. The proposed model significantly improves the ability to extract and utilize information. At the same time, transfer learning is used to ban the training of appliance models with similar characteristics, further reducing model complexity and training time. The experimental results based on the REDD dataset verify the method's effectiveness. Compared with the seq2seq and seq2point models, the proposed model achieved better accuracy and F1 score, up to 98.10% and 90.29%, respectively. At the same time, the proposed method is further verified on UK‐DALE, which proves that the proposed method has good portability and robustness. [ABSTRACT FROM AUTHOR]

A virtual power plant (VPP) is a solution that brings distributed generation (DG) resources together and allows them to be optimally utilized to meet load demands in the presence of technical and pollution constraints. Electricity, heat, and natural gas are interdependent at the levels of generation, transmission, and consumption, and the interactions of these energy sources need to be considered. This paper presents an optimal model for daily operation of a multi‐energy virtual power plant (MEVPP), including electric, thermal, and natural gas sectors. MEVPP includes small‐scale gas‐fired and non‐gas‐fired DGs, combined heat and power (CHP), power to gas (P2G), boilers, electrical storage, electric vehicles (EV), and thermal storage. Renewable energy resources (RES), including wind turbines (WT), photovoltaic (PV), and PV‐thermal (PVT), also supply P2G technology. Smart grid technologies such as price‐based demand response (PBDR) and incentive‐based demand response (IBDR) are employed for electric loads. The proposed MEVPP model is eligible to participate in day‐ahead electricity, natural gas, heat markets, and electrical spinning reserve market. The scheduling model is multi‐objective to maximize MEVPP profit and minimize carbon dioxide emissions. The Epsilon constraint method is utilized to solve the problem, and the best Pareto point is chosen using the fuzzy satisfying approach. [ABSTRACT FROM AUTHOR]

As demand for electric vehicles (EV) grows, interest in vehicle‐to‐grid (V2G) is increasing. Although V2G provides additional flexibility for power systems, it can be an inconvenience for the EV owner and shorten the cycle life of EV batteries. In this paper, we propose a power‐imbalance‐based droop control (PIDC) for V2G, which uses estimated active power imbalance between supply and demand, without any communications or dispatch signal from the automatic generation control (AGC). Unlike the existing frequency droop control, the proposed method controls V2G based on the estimated imbalance. The Imbalance between electricity supply and demand was estimated using the swing equation, frequency deviation, and rate of change of frequency (RoCoF). Conventional frequency droop control has a slow response speed because it only considers the frequency deviation. Using the PIDC, the critical frequency drop was discerned faster and the V2G could react more quickly in critical frequency drop situations. Additionally, battery cycle life was preserved in ordinary frequency fluctuations where V2G is unnecessary. This study used MATLAB R2020a to show the effectiveness and performance of PIDC. The case study results showed that PIDC has a faster response speed and preserves EV battery cycle life compared to frequency droop control. [ABSTRACT FROM AUTHOR]

The short‐term electricity consumption forecasting can help to ensure the safe and reliable operation of the power system. Power companies usually need to report the electricity consumption of the current month five to seven days in advance and make a power generation plan for the next month. The existing studies are usually lack of appropriate feature selection methods and hard to achieve satisfactory results. This paper proposes a short‐term electricity consumption forecasting approach based on feature processing and hybrid modelling. The maximum information coefficient (MIC) is employed to analyse the feature correlation, the electricity consumption curves are converted to several sub‐sequences of different frequency bands by the variational mode decomposition (VMD) to describe signal characteristics accurately, a hybrid model based on bidirectional gated recurrent unit (BiGRU) is innovated to extract the temporal and spatial features of the data and capture the contextual information from the complete time series, attention mechanism is used to do extract useful information and assign weights to make forecast. Compared with several benchmark methods, the proposed approach achieves better electricity consumption curve fitting and higher forecasting accuracy with the increase of forecasting step size. [ABSTRACT FROM AUTHOR]

This paper presents a practical optimal planning of solar photovoltaic (SPV) and battery storage system (BSS) for electric vehicle (EV) owner households with time of use (TOU) electricity pricing. The main aim of the optimisation problem is to minimize the Cost of Electricity (COE) while satisfying the design constraints over 20‐year project lifespan. Novel rule‐based home energy management systems are created to investigate the optimal sizing of two system configurations: (1) SPV‐EV, and (2) SPV‐BSS‐EV. The arrival and departure times of the EV's availability, as well as its initial state‐of‐charge are incorporated into the energy management system via stochastic functions. Sensitivity analyses of the feed in tariff, grid constraint, electricity demand, and available rooftop area are provided to investigate the variations of cost of electricity and capacities of SPV and BSS. From the study results, practical guidelines for grid‐connected households, based on TOU energy pricing, are provided to select the optimal capacity of SPV and BSS to accommodate the existing EV. The optimisation method is general and applicable to any household owning EV; however, in this study realistic data of solar insolation and temperature as well as household electricity demand and electricity prices are implemented for South Australia. Uncertainty analysis is investigated based on 10‐year real and stochastic data to prove the optimal results. It is found that the optimal configuration for a typical SA household utilising TOU pricing with an EV requires a 10‐kW SPV with a 10‐kWh capacity of BSS. [ABSTRACT FROM AUTHOR]

Real-time pricing is an attractive tariff for demand response programs, in which consumers could provide load flexibility by adjusting their electricity consumption in response to timevarying electricity prices. This paper reveals a new threat called real-time pricing response attack (RPRA), which manipulates consumers' electricity consumption by tampering with electricity price signals. Simulations are performed in IEEE 24-bus, 39-bus, and 118-bus systems, and the results show that 8%to 28% of the transmission lines could be overloaded by the attack, which could cause serious security problems. Results of sensitivity analysis indicate that the attack effects are influenced by various factors, such as DR models, price elasticity, line capacities etc. To defend against the RPRA attack, we have proposed various detection and mitigation strategies. [ABSTRACT FROM AUTHOR]

Ancillary service provision and peak shaving (PS) play essential roles in the current day‐to‐day power system operation, which is challenged by the increasing renewable generation penetration. Providing these critical services using classical approaches such as peak load generators has been limited due to high operational costs and environmental impacts. The use of battery energy storage systems (BESS) is another popular method that is limited by high initial investment costs and high degradation rates. In this work, a novel approach to utilize industrial loads and BESS to provide multiple power system services in different stages is proposed. Industrial loads such as aluminium crushers are known for their intensive electricity consumption. Nevertheless, when applied in frequency regulation (FR), they perform poorly due to their discrete nature in operation. This drawback and the aforementioned BESS shortcomings are addressed by combining on‐site BESS with plant machinery to provide FR services and recover BESS related costs. Later, depending on the optimal capacity distribution, BESS usage is extended into the energy arbitrage market to provide PS services. This approach resulted in higher earnings for participating customers and network operators, as well as in less CO2${\rm {CO}}_{2}$ emissions, and minimal BESS degradations. An Australian case study of the South West Interconnected System, along with Worsley Alumina refinery data of Western Australia has been used to showcase the model performances. [ABSTRACT FROM AUTHOR]

Here, a novel tri‐level energy market model aimed at addressing the challenges posed by demand side management (DSM) in the electricity distribution company (EDC) is introduced. DSM has emerged as a new strategy employed by EDCs to manage and control electricity demand by encouraging end‐users to modify their electricity consumption patterns. This is achieved through the participation of demand response (DR) aggregators, which play a crucial role in assisting end‐users with strategies and technologies to reduce their electricity consumption during peak hours. The proposed tri‐level energy market model consists of four distinct players: EDC, microgrids, aggregators, customers. The interactions between these four actors are modelled within a tri‐level game framework, where the EDC and aggregators act as leaders, and the micro‐grids and customers are followers. This multi‐level and multi‐player game structure allows for a more realistic representation of the complexities involved in DSM programs within the energy market. To demonstrate the effectiveness of the proposed model, a real case study is utilized, showing that the new model better resembles real‐life market conditions. The results illustrate how the tri‐level energy market model can significantly reduce demand fluctuations during peak hours, leading to improved efficiency and effectiveness within DSM programs. [ABSTRACT FROM AUTHOR]

The increasing demand for electricity in daily life highlights the need for Smart Cities (SC) to use energy efficiently. Both technical and Non‐Technical Losses (NTL), particularly those resulting from electricity theft, present powerful obstacles; NTL alone can reach billions of dollars. Although Machine Learning (ML) based approaches for NTL detection have been embraced by numerous utilities, there is still a lack of thorough analysis of these methods. Limited research exists on NTL identification evaluation criteria and unbalanced data management in the context of SC. This research compares ML algorithms and data balancing methods to optimize electricity consumption detection. The given research applied the 15 ML techniques of Logistic regression, Bernoulli naive Bayes, Gaussian naive Bayes, K‐Nearest Neighbour, perceptron, passive‐aggressive classifier, quadratic discriminant analysis, SGD classifier, ridge classifier, linear discriminant analysis, decision tree, nearest centroid classifier, multi‐nomial naive Bayes, complement naive Bayes and dummy classifier. While SMOTE, AdaSyn, NRAS, and CCR are considered for data balancing. AUC, F1‐score, and seven relevant performance metrics were used for comparison. We have also implemented SHapely Additive exPlanations (SHAP) for feature importance and model interpretation. Results show varying classifier performance with different balancing methods, emphasizing data preprocessing's role in NTL detection for smart grid security. [ABSTRACT FROM AUTHOR]

Electricity theft is a primary concern for utility providers, as it leads to substantial financial losses. To address the issue, a novel extreme gradient boosting (XGBoost)‐based model utilizing the consumers' electricity consumption patterns for analysis is proposed for electricity theft detection (ETD). To remove the imbalance in the real‐world electricity consumption dataset and ensure an even distribution of theft and non‐theft data instances, six different artificially created theft attacks were used. Moreover, the utilization of the XGBoost algorithm for classification, especially to identify malicious instances of electricity theft, yielded commendable accuracy rates and a minimal occurrence of false positives. The proposed model identifies electricity theft specific to the regions, utilizing electricity consumption parameters, and other variables as input features. The authors' model outperformed existing benchmarks like k‐neural networks, light gradient boost, random forest, support vector machine, decision tree, and AdaBoost. The simulation results using the false attacks for balancing the dataset have improved the proposed model's performance, achieving a precision, recall, and F1‐score of 96%, 95%, and 95%, respectively. The results of the detection rate and the false positive rate (FPR) of the proposed XGBoost‐based detection model have achieved 96% and 3%, respectively. [ABSTRACT FROM AUTHOR]

Demand side management (DSM) consists of planning, executing, and controlling activities to reduce electricity consumption. By using demand response (DR), customers help reduce demand during peak times. Consumer participation in DSM depends on his behaviour. Consumer behaviour is determined by factors such as lifestyle, electricity price, electricity consumption tariff, contract type etc. Thus, factors affecting the consumer's behaviour should be considered in order to determine more accurately the amount of participation in DSM programs. This article presents a model for the optimal scheduling of distributed energy resources by taking into account factors related to consumer behaviour. To reduce the volume of the DR data while maintaining the main features, distributed principal component analysis (D_PCA) was used to reduce the volume of DR data. Also, by integrating this method with the accelerated hybrid alternating direction method of multipliers (AHADMM) algorithm, an adapted and accelerated method is achieved to realize the reliability and cyber security of the system. The case study was conducted on the IEEE 118 bus power system at different levels of demand, which verified proposed meta‐algorithm improved at least between 4 to 13 iterations of energy resource convergence speed compared to similar methods and while DR is also intended. [ABSTRACT FROM AUTHOR]

The explosive demand for electricity and ecological concerns has necessitated the operation of power networks in a more cost‐effective approach. In recent years, the integration of combined heat and power units has presented a potential answer to these problems; nevertheless, a new difficult challenge has emerged: finding an optimal solution for simultaneous dispatch of power and heat. Therefore, to tackle this problem, this work presents an intelligent sequential algorithm based on a hybridization of an enthusiasm‐aided teaching and learning‐based optimization algorithm (ETLBO) with an improved version of particle swarm optimization (IPSO). The proposed method can simultaneously minimize total generating costs while considering a variety of physical and operational limitations. In addition, this research designed an adaptive violation constraint management approach combined with the formulated hybridized optimization algorithm to ensure system constraints' safe preservation during the optimization process. Finally, the performance of the proposed method is compared to the recently developed metaheuristic algorithms as well as Knitro and IPOPT (industrially used optimization packages), in which the ETLBO‐IPSO outperforms all the other methods. [ABSTRACT FROM AUTHOR]