Due to the development of photovoltaic (PV) technology and the support from governments across the world, the conversion efficiency of solar energy has been improved. However, the PV power output is influenced by environment factors, resulting in features of randomness and intermittency. These features may have a negative influence on power systems. As a result, accurate and timely power prediction data is necessary for power grids to absorb solar energy. In this paper, we propose a new PV power prediction model based on the Gradient Boost Decision Tree (GBDT), which ensembles several binary trees by the gradient boosting ensemble method. The Gradient Boost method builds a strong learner by combining weak learners through iterative methods and the Decision Tree is a basic classification and regression method. As an ensemble machine learning algorithm, the Gradient Boost Decision Tree algorithm can offer higher forecast accuracy than one single learning algorithm. So GBDT is of value in both theoretical research and actual practice in the field of photovoltaic power prediction. The prediction model based on GBDT uses historical weather data and PV power output data to iteratively train the model, which is used to predict the future PV power output based on weather forecast data. Simulation results show that the proposed model based on GBDT has advantages of strong model interpretation, high accuracy, and stable error performance, and thus is of great significance for supporting the secure, stable and economic operation of power systems.

In this paper, an intelligent energy management framework with demand response capability was proposed for industrial facilities. The framework consists of multiple components, including industrial processes modeled by the state task network (STN) method, thermostatically controlled loads (TCLs) like the heating, ventilation and air conditioning (HVAC) system with chilled water storage (CWS), renewable generation like photovoltaic (PV) arrays and electric vehicles (EVs). These components were firstly modeled and the operation of them is then optimized in time-of-use (TOU) pricing schemes. Factors that affect several components at the same time, e.g. the number of workers, are considered. The optimization is formulated as a mixed integer linear programming (MILP) problem. A general tire manufacturing facility was investigated as the case study. Simulation results show that the proposed intelligent industrial energy management (IIEM) with DR is able to effectively utilize the flexibility contained in all parts of the facility and reduce the electricity costs as well as the peak demand of the facility, while satisfying all the operating constraints.

Under frequency load shedding (UFLS) and under voltage load shedding (UVLS) are effective methods to maintain the power balance of and prevent frequency or voltage collapse of power systems. With the construction of wide area measurement systems, the development of demand response technologies and the application of smart appliances, a new direction for load shedding method emerges under the background of smart grid. In this paper, an intelligent UFLS/UVLS method based on the active participation of smart appliances is proposed. First, this paper takes refrigerators and water heaters as research objects, establishes their practical models and proposes a suitable control method for intelligent load shedding. Then an intelligent UFLS/UVLS method is proposed and simulated in IEEE 39-bus system. Simulation results prove that this strategy can work well to suppress the frequency and voltage fall or even collapse, and reduce the amount of load shedding and economic losses.

A standalone wind/solar/battery hybrid power system, making full use of the nature complementarity between wind and solar energy, has an extensive application prospect among various newly developed energy technologies. The capacity of the hybrid power system needs to be optimised in order to make a tradeoff between power reliability and cost. In this study, each part of the wind/solar/battery hybrid power system is analysed in detail and an objective function combining total owning cost and loss of power supply probability is built. To solve the problems with non‐linearity, complexity and huge computation, an improved particle swarm optimisation (PSO) algorithm is developed, which integrates the taboo list to broaden the search range and introduces ‘restart’ and ‘disturbance’ operation to enhance the global searching capability. The simulation results indicate that the proposed algorithm is more stable and provides better results in solving the optimal allocation of the capacity of the standalone wind/solar/battery hybrid power system compared with the standard PSO algorithm.

In order to effectively identify complex power quality disturbances, a power quality disturbance classification method based on empirical wavelet transform and a multi-layer perceptron extreme learning machine (ELM) is proposed. The model uses the discrete wavelet transform (DWT) multi-resolution method to extract classification features. Combined with hierarchical ELM (H-ELM) characteristics, the particle swarm optimization (PSO) single-object feature selection method is used to select the optimal feature set. The hidden layer of the H-ELM classifier in the model is trained by forward training. Once the previous layer is established, the weight of the current layer can be fixed without fine-tuning. Therefore, the training speed can be accelerated, the recognition accuracy is almost independent of the parameter adjustment, and the model has strong robustness. In order to solve the problem of data imbalance in the actual power system, a data enhancement method is proposed to reduce the impact of data imbalance and enhance the generalization performance of the network. The simulation results showed that the proposed method can identify 16 disturbances efficiently and accurately under different noise conditions, and the robustness of the proposed method is verified by the measured data.

With the increasing proportion of photovoltaic (PV) power in power systems, the problem of its fluctuation and intermittency has become more prominent. To reduce the negative influence of the use of PV power, we propose a short-term PV power prediction model based on the online sequential extreme learning machine with forgetting mechanism (FOS-ELM), which can constantly replace outdated data with new data. We use historical weather data and historical PV power data to predict the PV power in the next period of time. The simulation result shows that this model has the advantages of a short training time and high accuracy. This model can help the power dispatch department schedule generation plans as well as support spatial and temporal compensation and coordinated power control, which is important for the security and stability as well as the optimal operation of power systems.