Considering the electricity price’s volatility and various elements which affect the price in the electricity market, the paper presents hybrid model for the day-ahead electricity market clearing price forecasting. T...
详细信息
Considering the electricity price’s volatility and various elements which affect the price in the electricity market, the paper presents hybrid model for the day-ahead electricity market clearing price forecasting. The paper adopts autoregressive moving average (ARMAX) model to reveal the linear relationship between power load and electricity price;the generalized autoregressive conditional heteroskedasticity (GARCH) model to reveal the heteroskedasticity properties of residual. Simultaneously the paper presents the inexactness and irrationality that modeling by the historical data long ago to forecast the price with the change of the time, then presents the rolling forecast that constantly using the latest data to modeling the ARMAX-AR-GARCH model. To reveal the nonlinear relationship between power load and electricity price, the paper adopts least squares support vector machine (LS-SVM). Using the proposed method, the day-ahead electricity prices of California electricity market are forecasted, prediction results show the efficiency of the proposed method.
In this paper, genetic algorithm and modified dynamic programming are applied to path planning of robotic fish for the first time. Using grid method to the environment modeling and applying genetic algorithm to the pa...
详细信息
The least squares support vector machine (LS-SVM) is sensitive to noises or outliers. To address the drawback, a new robust least squares support vector machine (RLS-SVM) is introduced to solve the regression problem ...
详细信息
The least squares support vector machine (LS-SVM) is sensitive to noises or outliers. To address the drawback, a new robust least squares support vector machine (RLS-SVM) is introduced to solve the regression problem with outliers. A fuzzy membership function, which is determined by heuristic method, is assigned to each training sample as a weight. For each data point, firstly a deleted input neighborhood is found when the high-dimension feature space of input is focused on. Then the new field is reformulated after the output is brought in the neighborhood which we have found. The fuzzy membership function (weight) is set according to the distance from the data point to the center of its neighborhood and the radius of the neighborhood, which implies the probability to be an outlier. Two benchmark simulation experiments and analysis are presented to verify that the performance is improved.
A novel control algorithm is applied to control superheated steam temperature in power plants. Since the disturbances existed in practical processes are probably non-Gaussian, the performance index is constructed by m...
详细信息
A novel control algorithm is applied to control superheated steam temperature in power plants. Since the disturbances existed in practical processes are probably non-Gaussian, the performance index is constructed by minimizing the entropy and mean value of tracking error besides the constraints on control energy. The optimal control solution is given and applied to control superheated steam temperature in a power plant. The simulation results verify its effectiveness.
A novel control algorithm is applied to control superheated steam temperature in power plants. Since the disturbances existed in practical processes are probably non-Gaussian, the performance index is constructed by m...
详细信息
Market clearing price (MCP) forecasting techniques is very important for the development of the electricity market. A three-layered neural network is used to predict electricity prices. MCP is seen as a multi-input si...
详细信息
Market clearing price (MCP) forecasting techniques is very important for the development of the electricity market. A three-layered neural network is used to predict electricity prices. MCP is seen as a multi-input single-output system and the historical electricity price and load data is utilized in an electricity market. The neural network is based on Minimum Entropy Error (MEE) cost function and Batch-Sequential mode. Compared with other models, the proposed approach improves the prediction accuracy and speed.
A neural based PID feedback control method for networked process controlsystems is presented. As there are some uncertain factors such as external disturbance, randomly delayed measurements or control demands in real...
详细信息
In this paper, genetic algorithm and modified dynamic programming are applied to path planning of robotic fish for the first time. Using grid method to the environment modeling and applying genetic algorithm to the pa...
详细信息
In this paper, genetic algorithm and modified dynamic programming are applied to path planning of robotic fish for the first time. Using grid method to the environment modeling and applying genetic algorithm to the path planning, an optimal or sub-optimal robot path can be obtained. Since the robotic fish can't track linear motion, the robot path can be seen as several circular arc. Based on the optimal path obtained via genetic algorithm, modified dynamic programming algorithm is proposed to calculate the shortest circular arc path, fish velocity and direction in every step. Finally the experiment on the robotic fish control software shows the effectiveness of the proposed method.
This paper researches the consensus problem of high-order multi-agent systems. A new dynamic neighbor-based protocol is proposed which contains two parts, one is the local feedback and the other is the distributed fee...
详细信息
A neural based PID feedback control method for networked process controlsystems is presented. As there are some uncertain factors such as external disturbance, randomly delayed measurements or control demands in real...
详细信息
A neural based PID feedback control method for networked process controlsystems is presented. As there are some uncertain factors such as external disturbance, randomly delayed measurements or control demands in real networked process controlsystems, the proposed PID controller is implemented by backpropagation neural networks whose weights are updated via minimizing tracking error entropy of closed loop systems. To demonstrate the potential applications of the proposed strategy, an example of a simulated batch reactor is provided. The proposed design method is shown to be useful and effective in dealing with network process controlsystems.
暂无评论