Search

The state of charge (SOC) estimation of Li-ion batteries has attracted substantial interests in recent years. Kalman Filter has been widely used in real-time battery SOC estimation, however, to build a suitable dynamic battery state-space model is a key challenge, and most existing methods still use the off-line modelling approach. This paper tackles the challenge by proposing a novel sparse learning machine for real-time SOC estimation. This is achieved first by developing a new learning machine based on the traditional least squares support vector machine (LS-SVM) to capture the process dynamics of Li-ion batteries in real-time. The least squares support vector machine is the least squares version of the conventional support vector machines (SVMs) which suffers from low model sparseness. The proposed learning machine reduces the dimension of the projected high dimensional feature space with no loss of input information, leading to improved model sparsity and accuracy. To accelerate computation, mapping functions in the high feature space are selected using a fast recursive method. To further improve the model accuracy, a weighted regularization scheme and the differential evolution (DE) method are used to optimize the parameters. Then, an unscented Kalman filter (UKF) is used for real-time SOC estimation based on the proposed sparse learning machine model. Experimental results on the Federal Urban Drive Schedule (FUDS) test data reveal that the performance of the proposed algorithm is significantly enhanced, where the maximum absolute error is only one sixth of that obtained by the conventional LS-SVMs and the mean square error of the SOC estimations reaches to 10-7, while the proposed method is executed nearly 10 times faster than the conventional LS-SVMs.

Unit commitment is an intractable issue aiming to reduce the overall economic cost of power system operation while maintaining the system constraints. Due to the emerging scenario of global warming, many countries are vigorously developing renewable energy to replace the traditional fossil power plant, in order to reduce the environmental and carbon emission. The increasing penetration of renewable generation significantly challenge the economic and security of power system operation. In this paper, a low carbon multi-objective objective unit commitment model considering economic cost, environmental cost and, more importantly, the carbon emission is established, integrating wind and solar power and therefore generating a multi-objective, high-dimensional, strong non-linear, multi-constraint and mixed integer optimization problem. The non-dominated sorting genetic algorithm-III is tailored and adopted for solving the proposed challenging task, where the decision-making scheme is designed according to the normalization method and weighted sum function. Numerical results show that the proposed complex many-objective low carbon unit commitment model can be successfully solved by the proposed algorithm and the carbon emission is effectively reduced by the integration of renewable generations.

Lithium-ion batteries have been widely used as energy storage systems and in electric vehicles due to their desirable balance of both energy and power densities as well as continual falling price. Accurate estimation of the state-of-charge (SOC) of a battery pack is important in managing the health and safety of battery packs. This paper proposes a compact radial basis function (RBF) neural model to estimate the state-of-charge (SOC) of lithium battery packs. Firstly, a suitable input set strongly correlated with the package SOC is identified from directly measured voltage, current, and temperature signals by a fast recursive algorithm (FRA). Secondly, a RBF neural model for battery pack SOC estimation is constructed using the FRA strategy to prune redundant hidden layer neurons. Then, the particle swarm optimization (PSO) algorithm is used to optimize the kernel parameters. Finally, a conventional RBF neural network model, an improved RBF neural model using the two stage method, and a least squares support vector machine (LSSVM) model are also used to estimate the battery SOC as a comparative study. Simulation results show that generalization error of SOC estimation using the novel RBF neural network model is less than half of that using other methods. Furthermore, the model training time is much less than the LSSVM method and the improved RBF neural model using the two-stage method.

Efficient and valuable strategies provided by large amount of available data are urgently needed for a sustainable electricity system that includes smart grid technologies and very complex power system situations. Big Data technologies including Big Data management and utilization based on increasingly collected data from every component of the power grid are crucial for the successful deployment and monitoring of the system. This paper reviews the key technologies of Big Data management and intelligent machine learning methods for complex power systems. Based on a comprehensive study of power system and Big Data, several challenges are summarized to unlock the potential of Big Data technology in the application of smart grid. This paper proposed a modified and optimized structure of the Big Data processing platform according to the power data sources and different structures. Numerous open-sourced Big Data analytical tools and software are integrated as modules of the analytic engine, and self-developed advanced algorithms are also designed. The proposed framework comprises a data interface, a Big Data management, analytic engine as well as the applications, and display module. To fully investigate the proposed structure, three major applications are introduced: development of power grid topology and parallel computing using CIM files, high-efficiency load-shedding calculation, and power system transmission line tripping analysis using 3D visualization. The real-system cases demonstrate the effectiveness and great potential of the Big Data platform; therefore, data resources can achieve their full potential value for strategies and decision-making for smart grid. The proposed platform can provide a technical solution to the multidisciplinary cooperation of Big Data technology and smart grid monitoring.

Economic dispatch (ED) aims to allocate the generation of units to minimize the total production cost. This dispatch is generally formulated with nonsmooth and nonconvex cost function due to valve-point effects and various constraints, where the conventional methods are inapplicable. An improved social spider optimization algorithm, namely, ISSO, is proposed in this paper to solve the ED problem with valve-point effects. That is, dynamic updating mechanism of the subpopulations, Gaussian mating radius, and multimating strategy are introduced into the ISSO. These mechanisms facilitate a compromise between the global exploration and local exploitation of the search process. Numerical experiments are conducted on benchmark functions and different scale generation units commonly considered in the literature to validate the feasibility of the proposed ISSO. Computational results are analyzed in terms of solution quality by the statistical method, which shows the superiority of the ISSO algorithm in comparison with the state-of-the-art algorithms.

Load forecasting is one of the major challenges of power system operation and is crucial to the effective scheduling for economic dispatch at multiple time scales. Numerous load forecasting methods have been proposed for household and commercial demand, as well as for loads at various nodes in a power grid. However, compared with conventional loads, the uncoordinated charging of the large penetration of plug-in electric vehicles is different in terms of periodicity and fluctuation, which renders current load forecasting techniques ineffective. Deep learning methods, empowered by unprecedented learning ability from extensive data, provide novel approaches for solving challenging forecasting tasks. This research proposes a comparative study of deep learning approaches to forecast the super-short-term stochastic charging load of plug-in electric vehicles. Several popular and novel deep-learning based methods have been utilized in establishing the forecasting models using minute-level real-world data of a plug-in electric vehicle charging station to compare the forecasting performance. Numerical results of twelve cases on various time steps show that deep learning methods obtain high accuracy in super-short-term plug-in electric load forecasting. Among the various deep learning approaches, the long-short-term memory method performs the best by reducing over 30% forecasting error compared with the conventional artificial neural network model.

Short-term load forecasting is an important issue in energy management system and a key measure to maintain the stable and effective operation of power systems, providing reasonable future load curve feeding to the unit commitment and economic load dispatch. Specifically, load forecasting at different time scales has various and corresponding roles in power systems. In recent years, plug-in electric vehicles have gradually become popular in major cities, and the number of electric vehicles is growing rapidly. However, the mass roll out of EVs may cause severe problems to the power system due to the huge charging power and stochastic charging behaviours of the EVs drivers. The accurate model of EVs charging load forecasting is therefore an emerging topic. In this paper, artificial neural networks and a long short term memory model based deep learning approaches are employed and compared in forecasting the EVs charging load from the charging station perspective. Numerical results show that the long short term memory model has demonstrated better performance and provided a model of higher accuracy in short-term EVs load forecasting comparing with the traditional artificial neural networks.

Short-term load forecasting is a key task to maintain the stable and effective operation of power systems, providing reasonable future load curve feeding to the unit commitment and economic load dispatch. In recent years, the boost of internal combustion engine (ICE) based vehicles leads to the fossil fuel shortage and environmental pollution, bringing significant contributions to the greenhouse gas emissions. One of the effective ways to solve problems is to use electric vehicles (EVs) to replace the ICE based vehicles. However, the mass rollout of EVs may cause severe problems to the power system due to the huge charging power and stochastic charging behaviors of the EVs drivers. The accurate model of EV charging load forecasting is, therefore, an emerging topic. In this paper, four featured deep learning approaches are employed and compared in forecasting the EVs charging load from the charging station perspective. Numerical results show that the gated recurrent units (GRU) model obtains the best performance on the hourly based historical data charging scenarios, and it, therefore, provides a useful tool of higher accuracy in terms of the hourly based short-term EVs load forecasting.

The unit commitment (UC) problem is a critical task in power system operation process. The units realize reasonable start-up and shut-down scheduling and would bring considerable economic savings to the grid operators. However, unit commitment is a high-dimensional mixed-integer optimisation problem, which has long been intractable for current solvers. Competitive swarm optimizer is a recent proposed meta-heuristic algorithm specialized in solving the high-dimensional problem. In this paper, a novel binary competitive swarm optimizer (BCSO) is proposed for solving the UC problem associated with lambda iteration method. To verify the effectiveness of the proposed algorithm, comprehensive numerical studies on different sizes units ranging from 10 to 100 are proposed, and the algorithm is compared with other counterparts. Results clearly show that BCSO outperforms all the other counterparts and is therefore completely capable of solving the UC problem.

Conventional unit commitment is a mixed integer optimization problem and has long been a key issue for power system operators. The complexity of this problem has increased in recent years given the emergence of new participants such as large penetration of plug-in electric vehicles. In this paper, a new model is established for simultaneously considering the day-ahead hourly based power system scheduling and a significant number of plug-in electric vehicles charging and discharging behaviours. For solving the problem, a novel hybrid mixed coding meta-heuristic algorithm is proposed, where V-shape symmetric transfer functions based binary particle swarm optimization are employed. The impact of transfer functions utilised in binary optimization on solving unit commitment and plug-in electric vehicle integration are investigated in a 10 unit power system with 50,000 plug-in electric vehicles. In addition, two unidirectional modes including grid to vehicle and vehicle to grid, as well as a bi-directional mode combining plug-in electric vehicle charging and discharging are comparatively examined. The numerical results show that the novel symmetric transfer function based optimization algorithm demonstrates competitive performance in reducing the fossil fuel cost and increasing the scheduling flexibility of plug-in electric vehicles in three intelligent scheduling modes.

Decreasing initial costs, the increased availability of charging infrastructure and favorable policy measures have resulted in the recent surge in plug-in electric vehicle (PEV) ownerships. PEV adoption increases electricity consumption from the grid that could either exacerbate electricity supply shortages or smooth demand curves. The optimal coordination and commitment of power generation units while ensuring wider access of PEVs to the grid are, therefore, important to reduce the cost and environmental pollution from thermal power generation systems, and to transition to a smarter grid. However, flexible demand side management (DSM) considering the stochastic charging behavior of PEVs adds new challenges to the complex power system optimization, and makes existing mathematical approaches ineffective. In this research, a novel parallel competitive swarm optimization algorithm is developed for solving large-scale unit commitment (UC) problems with mixed-integer variables and multiple constraints – typically found in PEV integrated grids. The parallel optimization framework combines binary and real-valued competitive swarm optimizers for solving the UC problem and demand side management of PEVs simultaneously. Numerical case studies have been conducted with multiple scales of unit numbers and various demand side management strategies of plug-in electric vehicles. The results show superior performance of proposed parallel competitive swarm optimization based method in successfully solving the proposed complex optimization problem. The flexible demand side management strategies of plug-in electric vehicles have shown large potentials in bringing considerable economic benefit.

This paper proposed a Big Data platform solution for city power grid status estimation, with an in-memory distributed computing frame for power grid heterogeneous data analysis. A big data management system is proposed for managing high volume, heterogeneous and multi-mode power data. In addition, a high efficiency data-computing engine, a parallel computing model for power engineering and a 3D display system are consisted. Based on the platform, three real-system application cases are given in order to illustrate the practicability of the proposed platform, including high efficiency power grid load shedding computing and analysis, voltage sag association rule mining with 3D display, and real-time dynamic evaluation of operation status of wind farm units. As a conclusion, big data platform is a key technology to sufficiently realize the potential advantages of power data resources, and it can provide solid technological bases for the development of modern Smart Grid.

The majority of embedded systems are designed for specific applications, often associated with limited hardware resources in order to meet various and sometime conflicting requirements such as cost, speed, size and performance. Advanced intelligent heuristic optimization algorithms have been widely used in solving engineering problems. However, they might not be applicable to embedded systems, which often have extremely limited memory size. In this paper, a new compact teaching-learning based optimization method for solving global continuous problems is proposed, particularly aiming for neural network training in portable artificial intelligent (AI) devices. Comprehensive numerical experiments on benchmark problems and the training of two popular neural network systems verify that the new compact algorithm is capable of maintaining the high performance while the memory requirement is significantly reduced. It offers a promising tool for continuous optimization problems including the training of neural networks for intelligent embedded systems with limited memory resources.

To tackle with the urgent scenario of significant green house gas and air pollution emissions, it is pressing for modern power system operators to consider environmental issues in conventional economic based power system scheduling. Likewise, renewable generations and plug-in electric vehicles are both leading contributors in reducing the emission cost, however their integrations into the power grid remain to be a remarkable challenging issue. In this paper, a dual-objective economic/emission unit commitment problem is modelled considering the renewable generations and plug-in electric vehicles. A novel fast hybrid meta-heuristic algorithm is proposed combing a binary teaching-learning based optimization and the self-adaptive differential evolution for solving the proposed mix-integer problem. Numerical studies illustrate the competitive performance of the proposed method, and the economic and environmental cost have both been remarkably reduced.

Big Data technology has been introduced into power industry and seen breakthroughs in various aspects including system stability analysis, equipment fault detection, risk evaluation and etc. In order to improve the safety and stability of a city (Guangzhou, China) level power grid, a Big Data platform with 3D visualization is proposed in this study. Firstly, the lightning activities in Guangzhou area in recent years is analysed, and the operational status of power transmission lines and tripping records caused by lightning and storms are summarized. On this basis, the transient effects on voltage and current of the tripped transmission lines can be directly presented using 3D simulation system, thus the tripping events and the affected substations can be visualized. Moreover, Big Data mining technologies are applied to analyse the correlated factors of tripping events, such as the lightning and storms and other weather conditions, seeking for any potential links among the factors. Eventually, the proposed system can establish a correlative information database of lightning, tripping and other related factors for Guangdong power grid, and provide effective technical support for making protection principles of grid operation, carry out daily maintenance of lightning protection, and improve the operation level of the grid.

Integrated community energy systems have attracted considerable attention due to their capabilities in supporting distributed generation integration and providing various energy services to customers. However, the rising use of gas-fired generations at the community level is pushing the gas distribution network to its operational boundaries and preventing its further applications. This paper investigates the dynamic interactions and mutual dependence between community energy systems and the gas network through an integrated energy system model. The model incorporates the dynamic behaviors of the gas network, distributed generations and the relevant energy management system. Based on this model, disturbance propagations between the gas network and communities are analyzed from the viewpoint of energy exchanges. Numerical results demonstrate that the change of loads and solar panel outputs can cause large pressure drops of the gas network when microturbines are set to compensate for these variations, and the pressure drop can affect the operation of other gas-fired equipment in surrounding areas. The results also show that different communities can influence each other through the gas network, which indicates some coordination is required in order to restrain adverse interactions as well as their impacts on the gas network.

By supplying thermal and electric energies to host facilities, microgrids with combined heat and power can enhance the resilience of urban energy systems. However, the increasing use of gas-fired distributed generations is pushing gas distribution networks to their operating limits, which may cause significant adverse impacts on microgrids. This paper investigates the interactions between gas networks and microgrids from the viewpoint of integrated energy systems. Four operating modes of microgrids are discussed to describe their connections with external energy networks. A novel model for gas-fired distributed generations, particularly microturbines, is first proposed to capture the interactions between gas networks and microgrids. An integrated system model is then developed to characterize the behaviors of the interrelated gas network and microgrids under different scenarios. Numerical results demonstrate that the variation of microturbine outputs may cause a large pressure drop of the gas network, especially during the transient process of gas flow adjustments. The results also reveal that microgrids can alter the operations among themselves through the accessed gas network.

This paper presents a preliminary study of developing a novel platform for big data management, processing and analysis of modern power systems. The framework comprises a big data acquisition subsystem, a big data analysis subsystem, a decision-making assistance subsystem and an information integration subsystem. For the big data management system, a novel structure is designed according to three different data resources, including database, data files and data stream. Further, powerful open-source computation algorithms and self-developed novel intelligent methods are integrated in the big data analysis system. To be specific, our early work on statistical processing monitoring (Principal Component Analysis (PCA)), advanced modelling methods (Fast Recursive Algorithm (FRA)) and newly developed optimization method (Teaching-Learning Based Optimization (TLBO)) are integrated into a self-developed analysis module. Thus, with the novel big data acquisition structure and data processing engine, the proposed platform can provide a powerful tool for big data analytic based Smart Grid monitoring.

Wind direction and speed are both crucial factors for wind farm layout, however, the relationship between the two factors has not been well addressed. To optimize wind farm layout, this study aims to statistically explore wind speed characteristics under different wind directions and wind direction characteristics. For this purpose, the angular&ndash, linear model for approximating wind direction and speed characteristics were adopted and constructed with specified marginal distributions. Specifically, Weibull&ndash, Weibull distribution, lognormal&ndash, lognormal distribution and Weibull&ndash, lognormal distribution were applied to represent the marginal distribution of wind speed. Moreover, the finite mixture of von Mises function (FVMF) model was used to investigate the marginal distribution of wind direction. The parameters of those models were estimated by the expectation&ndash, maximum method. The optimal model was obtained by comparing the coefficient of determination value (R2) and Akaike&rsquo, s information criteria (AIC). In the numerical study, wind data measured at a featured wind farm in north China was adopted. Results showed that the proposed joint distribution function could accurately represent the actual wind data at different heights, with the coefficient of determination value (R2) of 0.99.