Online Operation Risk Assessment of the Wind Power System of the Convolution Neural Network (CNN) Considering Multiple Random Factors
Round 1
Reviewer 1 Report
Summary of the paper:
The paper presents an online operation risk assessment of wind power system of the convolution neural network (CNN) considering multiple random factors of uncertain wind power output, load fluctuations, frequent changes in operation, electrical equipment failure rate.
The paper presents an argument concerning an interesting topic, but it cannot be published in the present form. I recommend a Minor Revision of the paper.
For this work, the main comments are summarized as follows:
1.The novelty and the main goal of the paper are sufficiently clear.
2.For each reference cited in the paper, please indicate first author et al.
3.Avoid using acronyms without specifying their meaning (e.g. line 79).
4.Avoid repeating the title in the paper (e.g. line 85-87).
5.Title and abstract are sufficiently clear. The abstract summarizes the points treated within the paper; however, the Authors should provide some data in showing the main results (from a numerical point of view) of their research: in this way, they can better summarize the goodness of their study and the principal findings of their work.
6.A proof reading by a native English speaker should be conducted to improve the language. There are many grammatical errors and spelling mistakes in this article (Lines 48, etc.). These errors can be regulated carefully.
7.A careful reading of the paper is needed to eliminate typos (e.g. line 68, 77, Eq. 2, 230, 263, 266, 390, etc.).
8.The structure of the paper could be improved: adding a Section “Methodology”, the general description of the methodology will be clearer, allowing a better comprehension of how the work was carried out.
9.The bibliography needs to be implemented. A more elaborated bibliographic research should be provided. The literature review should be extended, indicating some recently published work to better.
10.Figure 1 has too small characters, so it is not readable. Please, enlarge the characters and write the UM in square brackets.
11.Figure 2 has too small characters, so it is not readable. Please, enlarge the characters, write the UM in square brackets and add a clear description of the figure.
12.The meaning of Figure 3 is not clear.
13.Line 268. Please indicate the number of the figure.
14.Line 271. Sentence “For the data obtained from the data, …” is not clear. Please, rewrite the sentence.
15.Figure 7 has too small characters, so it is not readable. Please, enlarge the characters.
16.Figure 9, figure 10, table 2, table 3, table 4, table 5. Add a clear description of figures and table in their captions.
17.Table 2. Add Units of measurement for each variable.
18.The conclusions should be rewritten in a better and more clearly way, highlighting the main findings achieved in the work. Some sentences are difficult to understand (e.g. line 558-562, line 565-566, etc).
Author Response
Point 1: The novelty and the main goal of the paper are sufficiently clear.
Point 2: For each reference cited in the paper, please indicate first author et al.
Response 2:
Some scholars and experts have conducted research in this area, such as [3], in which Feng et al. propose an online risk index of power-system static voltage security. However, the disadvantage is the low accuracy of calculation. In [4], Zhang put forward a control strategy and method to improve the safety and reliability of distribution network operation. The risk value corresponding to the current operating state of the transmission line directly affects the safe operating level of the entire system [5-6]. Risk assessment studies are mostly focused on the construction of physical models, but inherent shortcomings of physical models still exist. In [7-9], Wang, Khan, and Du et al. presents a real-time video face recognition method based on the convolution neural network (CNN) and a large number of typical fault case descriptive text data accumulated in the information work of power grid companies have been extracted from the fault case by means of text mining technology. Lv’s study [10] adopts the target detection model based on the deep learning method in the built intelligent detection system to prevent external force damage, improves the network structure, increases the number of network layers, and enhances the ability to identify targets. In Niu and Cui’s work [11-12], historical wind power data from wind farms and numerical weather forecast data such as wind speed and wind direction are used as the input, and the convolution neural network (CNN) is integrated on the basis of the traditional gate controlled circulation unit (GRU) neural network to improve the ability to extract raw data and reduce the dimensions. Introduction of the dropout calculation is also employed to reduce the phenomenon of over fitting. In [13-14], Shi and Wang et al. describe the use of the CNN algorithm in the detection of unmanned aerial vehicle (UAV) power line inspection image components, and verify the approach with the actual sampled power component inspection data. In [15], Huang et al. introduce and compare the deep learning models of the regional convolution neural network, fast regional neural network, and faster neural network 3 for target recognition. CNN's advantages are obvious. It has begun to be widely used in forecasting, model identification, and fault identification in power systems, but it is also relatively less used for the online risk assessment of wind power systems.
Point 3: Avoid using acronyms without specifying their meaning (e.g. line 79).
Response 3: (e.g. line 79) ——In [13-14], Shi and Wang et al. describe the use of the CNN algorithm in the detection of unmanned aerial vehicle (UAV) power line inspection image components, and verify the approach with the actual sampled power component inspection data.
Point 4: Avoid repeating the title in the paper (e.g. line 85-87).
Response 4:（e.g. line 85-87）—— In response to the above problems, this paper proposes the convolution neural network (CNN) online operation risk assessment model considering multiple random factors in the wind power system.
Point 5: Title and abstract are sufficiently clear. The abstract summarizes the points treated within the paper; however, the Authors should provide some data in showing the main results (from a numerical point of view) of their research: in this way, they can better summarize the goodness of their study and the principal findings of their work.
Response 5:
In this paper, the CNN is introduced into the online operation risk assessment of power systems, and an online operation risk assessment of the wind power system of the convolution neural network considering multiple random factors is proposed. By analyzing multiple random factors of online risk assessment of the wind power system, and extracting uncertain wind power output data, load fluctuations data, frequent changes in operation patterns, and electrical equipment failure rate data, combined with the expected target of online operation risk assessment, we built sample data for CNN training. After the CNN algorithm is used for offline training, the optimal online operation risk assessment model of the wind power system was obtained. Finally, the trained evaluation model was applied to the online real-time monitoring system data, and the results of the rapid and accurate online operation risk assessment were obtained. The model presented in this paper was verified by simulation by the standard network of 39 nodes of 10 machines of the New England system. The online risk assessment results of the CNN model simulation are the same as the results of the conventional evaluation model. For example, for the first dispatch time, the CNN model risk assessment value is 0.6104, which means the risk rating is IV and the conventional model value is 1, which means that the risk rating is IV; the application of the CNN model simulation time is 0.181 s, which is very short, and far less than the simulation time of the conventional evaluation model, for which the time is 297.315 s. The case studies indicate the following: 1) The CNN model is more accurate when considering multiple random factors, such as the wind power output uncertainty, load fluctuation, operation pattern change, and the electrical equipment failure rate, when compared to considering a single factor causing the operation risk model; 2) the online operation risk assessment model of the wind power system uses the CNN for training implementation. The establishment of this assessment model is implemented in a data-driven manner instead of using the traditional physical assessment model, thus avoiding the process of establishing a complex physical assessment model and avoiding the simplification of multiple random factors. The original information of multiple random factors is preserved to ensure the accuracy of the model. The online operation risk assessment model of the wind power system presented in this paper adopts the CNN method, offline training sample data, and an online application training model. It is proved that the online operation risk assessment model is more rapid and suitable for online application.
Point 6: A proof reading by a native English speaker should be conducted to improve the language. There are many grammatical errors and spelling mistakes in this article (Lines 48, etc.). These errors can be regulated carefully.
Response 6: Even if the online operation risk assessment model is successfully established, the physical model is extremely ineffective in the actual online operation risk assessment application due to the simplified processing during the model establishment process and this reduces the accuracy of the model.
Point 7: A careful reading of the paper is needed to eliminate typos (e.g. line 68, 77, Eq. 2, 230, 263, 266, 390, etc.).
Response 7:
In [7-9], Wang, Khan, and Du et al. presents a real-time video face recognition method based on the convolution neural network (CNN) and a large number of typical fault case descriptive text data accumulated in the information work of power grid companies have been extracted from the fault case by means of text mining technology.
In Niu and Cui’s work [11-12], historical wind power data from wind farms and numerical weather forecast data such as wind speed and wind direction are used as the input, and the convolution neural network (CNN) is integrated on the basis of the traditional gate controlled circulation unit neural network to improve the ability to extract raw data and reduce the dimensions. Introduction of the dropout calculation is also employed to reduce the phenomenon of over fitting.
If the ith branch is scheduled for planned maintenance and the jth branch is scheduled for unplanned electrical equipment failure, the corresponding branch failure rate is
(2)
The SCADA system database can obtain (1) real-time power supply output data on the power supply side, (2) real-time load fluctuation data on the load side, and (3) network grid structure and telemetry data, and (4) other switching equipment operation data.
2s represents the first sub-sampling layer, and the sub-sampling layer and the convolution layer appear in pairs, so the first sub-sampling layer also has six layers, and the first sub-sampling layer data scale is 1/2 of the first convolution layer.
Point 8: The structure of the paper could be improved: adding a Section “Methodology”, the general description of the methodology will be clearer, allowing a better comprehension of how the work was carried out.
Response 8:
1. Introduction
2. Analysis of Multiple Random Factors of Online Risk Assessment of Wind Power System
2.1. Uncertain Wind Power Output
2.2. Load Fluctuations
2.3. Frequent Changes in Operation Patterns
2.4. Electrical Equipment Failure Rate Time-varying
2.5. Expected Targets of Online Operation Risk Assessment
3. Deep Convolutional Neural Network (CNN) Methodology
3.1. Convolution Layer
3.2. Sampling Layer
3.3. Fully Connected Layer
3.4. Output Layer
4. Online Operation Risk Assessment of Wind Power System of the CNN
4.1. General Framework Process
4.2. Multiple Random Factors Data Acquisition
4.3. Online Operation Risk Sample Generation
4.4. CNN Algorithm Implementation
5. Online Operation Risk Assessment Process
6. Case Study
6.1. Sample Data Composition for CNN Training
6.2. CNN Training Wind System Online Operation Risk Assessment Model
6.3. CNN Evaluation Model Application
7. Conclusions
References
3. Deep Convolutional Neural Network (CNN) Methodology
The deep convolution neural network (CNN) is a special deep learning artificial neural network consisting of an input layer (l), a convolution layer (C), a sampling layer (S), a fully connected layer (F), and an output layer (O). The convolution layer and the sampling layer alternate, and the output of the upper layer is the input of the next layer, finally forming the one-dimensional fully connected network [16]. The CNN structure is shown in Figure 1.
Figure 4. Convolutional Neural Network (CNN) Structure.
3.1. Convolution Layer
The convolution layer can be composed of multiple feature maps. The input is connected to the previous layer through the convolution core. Each neuron is partially connected to multiple characteristic charts of the upper layer. The convolution core corresponding to each neuron is different, ensuring that the feature is fully extracted [17]. Its output is
(7)
where Uol is the output of the convolution layer l; Xil-1 is the input of the convolution layer l; Kil is the corresponding convolution core; M is the input subset of the convolution layer l; f(.) is an activation function; Bl is plus offset; and “*” is the convolution symbol.
3.2. Sampling Layer
Each feature matrix of the S layer of the sampling layer corresponds to the C layer of the convolution layer one by one. Using local correlation, the characteristic diagram of the convolution layer is sampled and reduced in dimension. It can reduce the amount of data processing while retaining useful information [18]. The output is
(8)
where Uol is the output of the sampling layer l; f(.) is an activation function; βl is the weight coefficient of the sampling layer S; fdown(.) represents a sampling function; Xil-1 represents the input feature diagram of the sampling layer l; and Bl is the bias of the sampling layer.
3.3. Fully Connected Layer
The neurons of the full connected F layer in the CNN are all connected to the neurons of the upper layer. The two-dimensional feature diagram is spliced into a one-dimensional feature as the input of the fully connected network. The output is
(9)
where Uol is the output of the fully connected layer; wl is the weight coefficient; and Bl is the layer bias.
3.4. Output Layer
The output layer consists of the Euclidean radial basis function (ERBF) unit. The farther the input is from the parameter vector, the larger the ERBF output can be understood as a penalty item [19] that measures the degree of match between the input mode and a model associated with the ERBF class.
The loss function in the CNN is used to measure our dissatisfaction with the results. It can be expressed as a cross-entropy function:
(10)
Where yi is the actual value of the first label corresponding to the training set and y^i is the predicted value of the first label corresponding to the CNN training set.
CNN reverse propagation is based on the gradient descent method, so that the initial network parameters are adjusted in the direction of small error, and the accuracy of the classification is continuously improved.
Point 9: The bibliography needs to be implemented. A more elaborated bibliographic research should be provided. The literature review should be extended, indicating some recently published work to better.
Response 9:
1. Y.L. WANG, Y. TIAN, H.X. NI. Online Operation Risk Assessment of Power System Transmission Network Based on Line Parameter Measurement [J]. Hubei Electric Power, 2018(42):6-11
2. S.H, LI. Comments on Online Risk Assessment of Grid Operation [J]. Shang dong Industrial Technology, 2018(08):177-178
3. Y. FENG, Z.H. YUN, Q. ZHOU, J.W. SUN. Online Risk Assessment and Preventive Control Considering Wind-power integration [J]. Electric Power Automation Equipment,2017,37(2):61-68
4. Y.G. ZHANG. The Research on Risk Assessment of Distribution Equipment Based on Condition Monitoring [D]. Beijing: North China Electric Power University. 2016.06
5. S. LIU, L.F. LI, X.Q. SHI. The Power Transmission System Reliability Evaluation System and Application Research [J]. Hubei Electric Power, 2016, 40(02):13-18
6. Y.F. LIAO, G.J. YANG, W. GAO. Recognition Technology of Internal Overvoltage in Distribution Network Based on AD-CNN [J]. High Voltage Engineering, 2018, 12(08):9-15
7. Z.H. WANG. Research and Realization of Intelligent Video Analysis Technology in Unmanned Substation [D]. Beijing: School of Electric and Electronic Engineering. 2017.03
8. D. KHAN. Deep Learning Based Power Switch Detection and State Recognition [D]. Chengdu: University of Electronic Science and Technology of China. 2018.06
9. X.M. DU, J.F. QIN, S.Y. GUO. Text Mining of Typical Defects in Power Equipment [J]. High Voltage Engineering, 2018, 44(4):1078-1084
10. N. LV. Research on the Surveillance System of Preventing from External Damage for Transmission Line Based on Deep Learning [D]. Harbin: Harbin Engineering University. 2018.04
11. Z.W. NIU, Z.Y. YU, LI Bo. Short-term Wind Power Forecasting Model Based on Deep Gated Recurrent Unit Neural Network [J]. Electric Power Automation Equipment, 2018,38(5):36-42
12. S.J. Cui. Research on Power Load Forecast and Dispatch Based on Neural Networks [D]. Harbin: Qiqihar University. 2015.06
Point 10: Figure 1 has too small characters, so it is not readable. Please, enlarge the characters and write the UM in square brackets.
Response 10: the figure 1 is as following:
Figure 1. Power Output Curve.
Point 11: Figure 2 has too small characters, so it is not readable. Please, enlarge the characters, write the UM in square brackets and add a clear description of the figure.
Response 11: the figure 2 is as following:
Figure 2. Load Power Curve.
Figure 2 shows the load output curve of 96 dispatch points on one day of a load node. It can be seen from the figure that the load output curve is not smooth, and the load output changes many times, indicating that the load output fluctuation of the load node is frequent and obvious. There are many reasons for load fluctuations, including residents’ living habits, industrial power hours, motor starting and stopping methods, air-conditioning/heating use, and other reasons that directly affect the load output and result in fluctuations of the load output. Fluctuation of the load requires adjustment of the power supply output to keep it balanced. The power supply includes the power supply of the conventional unit and the power supply of the wind unit. Therefore, load fluctuation is also a random factor that cannot be ignored in the online operation risk assessment of wind power systems.
Point 12: The meaning of Figure 3 is not clear.
Response 12: For the language Figure 3. Network Topology. In Figure 3, the circle represents the injected power nodes. The injected power node includes the power access node and the load access node. The power value of the power access node is positive and the power value of the load access node is negative. The straight line represents the branch road in the grid structure, the solid straight line represents the actual branch line, and the virtual straight line represents the branch road of the planned maintenance, which means that the branch road that needs to be disconnected from the wind power system causes the topology of the grid to change. In the wind power system, there are many planned maintenance events, the number of branch strips for each planned maintenance event is different, and the branch positions for maintenance are different, resulting in frequent changes in the topology of the grid and frequent changes in the operation patterns of the wind power system. Unplanned electrical equipment failure can also cause fault branches to be disconnected from the wind power system, which in turn changes the topology of the wind power system grid. This situation is analyzed in the following section. When the operation pattern is changing, the virtual straight line will disconnect from the network and the structure of the network topology will be changed.
Point 13: Line 268. Please indicate the number of the figure.
Response 13:The SCADA system database can obtain (1) real-time power supply output data on the power supply side, (2) real-time load fluctuation data on the load side, and (3) network grid structure and telemetry data, and (4) other switching equipment operation data.
Point 14: Line 271. Sentence “For the data obtained from the data, …” is not clear. Please, rewrite the sentence.
Response 14:The data obtained is shown in the “Data Display”, for which the data is the online operation risk assessment of the wind power system.
Point 15: Figure 7 has too small characters, so it is not readable. Please, enlarge the characters.
Response 15: the figure 7 is as following:
Figure 7. Operation Risk Sample Data Generation Principle Diagram
Point 16: Figure 9, figure 10, table 2, table 3, table 4, table 5. Add a clear description of figures and table in their captions.
Response 16:
Figure 9. Training Structures Diagram
Figure 10. Application of the Convolution Neural Network (CNN) Training Model.
Table 2. Sample Data Generation
Feature Variables Variable Value Range Arranged Combination numbers
Wind Farm Output Pw (0.2/0.3/0.4/0.5/0.6/0.7/0.8/0.9/1.0)*50MW 9 kinds
Load Output PL (0.8/0.85/0.9/0.95/1.0/1.05/1.1/1.15/1.2)*PLN 9 kinds
Planned Maintenance ri1=1,Ri1=∞Ω C461 = 46 kinds
Unplanned Equipment Failure rj1=1,Rj1=∞Ω; rj2=1,Rj2=∞Ω C452 = 990 kinds
Risk Rating I, II, III, IV 4 kinds
Table 3. The Sample Data.
Input/groups Output/groups
Training Data 38 × 46 × 50000 4 × 50000
Test Data 38 × 46 × 10000 4 × 10000
Table 4. The test platform.
Project Parameter
System Version Windows 10 Pro. 64-bit
CPU Intel(R) Core (TM) i5-6200U
Processing Speed 2.40 GHz
RAM 8 GB
Table 5. The Different CNN Network Simulations.
No. Network Structure Convolution Core Batch Number Training Time Calculate Error Rate Training Time/s
1 6c-1s-12c-1s 3*3 3*3 50 2 0.6776 471.331
2 6c-1s-12c-1s 5*5 5*5 50 2 0.3402 661.027
3 6c-1s-12c-1s 7*7 7*7 50 2 0.6776 967.433
4 6c-1s-12c-1s 4*4 5*5 50 2 0.0402 661.670
5 6c-1s-12c-2s 4*4 4*4 50 2 0.3402 440.17
6 6c-1s-12c-2s 5*5 5*5 50 2 0.6776 608.454
7 6c-2s-12c-1s 5*5 5*5 50 2 0.3402 248.144
8 6c-2s-12c-1s 5*5 4*4 50 2 0.3204 202.517
9 6c-2s-12c-2s 5*5 4*4 50 2 0.0016 197.475
10 6c-2s-12c-2s 7*7 5*5 50 2 0.0502 278.023
11 1c-1s-1c-1s 1*1 1*1 50 2 0.3205 10.395
12 6c-1s-12c-1s 4*4 4*4 100 2 0.3402 575.209
13 6c-1s-12c-1s 4*4 4*4 500 2 0.3102 580.214
14 6c-1s-12c-1s 4*4 4*4 50 10 0.3402 296.052
15 6c-2s-12c-2s 5*5 4*4 50 10 0.0010 287.563
16 6c-2s-12c-2s 5*5 4*4 500 10 0.0021 190.264
Point 17: Table 2. Add Units of measurement for each variable.
Response 17:
Table 2. Sample Data Generation
Feature Variables Variable Value Range Arranged Combination numbers
Wind Farm Output Pw (0.2/0.3/0.4/0.5/0.6/0.7/0.8/0.9/1.0)*50MW 9 kinds
Load Output PL (0.8/0.85/0.9/0.95/1.0/1.05/1.1/1.15/1.2)*PLN 9 kinds
Planned Maintenance ri1=1,Ri1=∞Ω C461 = 46 kinds
Unplanned Equipment Failure rj1=1,Rj1=∞Ω; rj2=1,Rj2=∞Ω C452 = 990 kinds
Risk Rating I, II, III, IV 4 kinds
Point 18: The conclusions should be rewritten in a better and more clearly way, highlighting the main findings achieved in the work. Some sentences are difficult to understand (e.g. line 558-562, line 565-566, etc).
Response 18: Comparing Figure 18 and Figure 19, it can be seen that the values output in Figure 18 and Figure 19 are different at the same scheduling time, but the results of the characterization of online running risk ratings are the same. As shown in Figure 18, the output value of the first scheduling time is 0.6104, and the online operation risk is rated as IV; in Figure 19, the output value of the first scheduling time is 1, and the online running risk is graded as level IV. It indicates that the online risk assessment results of the CNN model simulation are the same as the results of the conventional evaluation model. By analogy, it can be proved that the online operation risk assessment of the wind power system using the CNN model is correct. In Table 6, the simulation time when using the CNN model and conventional evaluation model to evaluate the online operation risk of the wind power system is given. As can be seen from Table 6, the application of the CNN model simulation time is very short, being far less than the simulation time of the conventional evaluation model, indicating that the CNN model is more suitable for application in online operation risk assessment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The paper proposes an online operation risk assessment 14 of wind power system of the convolution neural network (CNN) considering various exogenous factors. The paper is in general well written and has an adequate scientific content. Nevertheless, the manuscript could be improved in terms of its accuracy and style by considering the following recommendations:
- Abscissa for Figure 1 could be represented in a better and intuitive manner (daytime or hourly). The same observations are also for the Figs. 14 and 15.
- May be the data from Table 5 could be represented in a better way, to make them easier to interpret and analyze
- All the acronyms and variable presented in eq. (4)—(6), are to be defined prior or immediately after their usage
- In the conclusion section, the authors should underline in a quantitative manner the paper added value to the field relative to the actual research stage of the field.
- English is to be revised throughout the paper
Author Response
Point 1: Abscissa for Figure 1 could be represented in a better and intuitive manner (daytime or hourly). The same observations are also for the Figs. 14 and 15.
Response 1:
Figure 1. Power Output Curve
Point 2: May be the data from Table 5 could be represented in a better way, to make them easier to interpret and analyse
Response 2:
The seventh storage of data event was trained and simulated under different CNN network structures. The simulation results are shown in Table 5.
Table 5. The Different CNN Network Simulations.
No. Network Structure Convolution Core Batch Number Training Time Calculate Error Rate Training Time/s
1 6c-1s-12c-1s 3*3 3*3 50 2 0.6776 471.331
2 6c-1s-12c-1s 5*5 5*5 50 2 0.3402 661.027
3 6c-1s-12c-1s 7*7 7*7 50 2 0.6776 967.433
4 6c-1s-12c-1s 4*4 5*5 50 2 0.0402 661.670
5 6c-1s-12c-2s 4*4 4*4 50 2 0.3402 440.17
6 6c-1s-12c-2s 5*5 5*5 50 2 0.6776 608.454
7 6c-2s-12c-1s 5*5 5*5 50 2 0.3402 248.144
8 6c-2s-12c-1s 5*5 4*4 50 2 0.3204 202.517
9 6c-2s-12c-2s 5*5 4*4 50 2 0.0016 197.475
10 6c-2s-12c-2s 7*7 5*5 50 2 0.0502 278.023
11 1c-1s-1c-1s 1*1 1*1 50 2 0.3205 10.395
12 6c-1s-12c-1s 4*4 4*4 100 2 0.3402 575.209
13 6c-1s-12c-1s 4*4 4*4 500 2 0.3102 580.214
14 6c-1s-12c-1s 4*4 4*4 50 10 0.3402 296.052
15 6c-2s-12c-2s 5*5 4*4 50 10 0.0010 287.563
16 6c-2s-12c-2s 5*5 4*4 500 10 0.0021 190.264
In Table 5, the second column is the network structure of the CNN, the third is the convolution core, the fourth is the batch number, the fifth is the training time, the sixth is the calculation error rate, and the seventh is the CNN training simulation time. Through the online operation risk assessment model of the wind power system trained by the CNN network, the first concern is the calculation error rate in model training; the lower the calculation error rate, the more accurate the model. Then, there is a focus on the training simulation time. From the table, it can be seen that the structural design of the volume layer and sampling layer, the selection of volume core, batch data processing, and the training times have an impact on the accuracy and simulation time of the CNN training model. Combined with the above reasons, it can be seen that the 6c-2s-12c-2s (5 * 5, 4 * 4) CNN network model has the lowest calculation error rate. As shown in Figure 14, the calculation error rate of this model is within the acceptable range. Therefore, a CNN network model of 6c-2s-12c-2s (5 * 5, 4 * 4) was selected to train the wind power system to run online risk assessment data. The trained CNN model can be considered as the online operation risk assessment model of the system; that is, the wind power system can be used as real-time data online running risk assessment.
Point 3: All the acronyms and variable presented in eq. (4)—(6), are to be defined prior or immediately after their usage
Response 3:
The severity of the load loss risk event can be expressed as
(4)
where Si is the severity of the ith node load loss event; Pwi is the wind farm output of the ith node; PGi is the access generator (including wind power units and conventional units) capacity of the ith node; and PLi is the access load capacity of the ith node.
(3) Risk Event Risk Value
The risk value of the load loss risk event can be expressed as
(5)
where Riski is the risk value of the ith node load loss event; Pri is the probability of the ith node load loss event; and Si is the severity of the ith node load loss event.
In order to intuitively reflect the online operation risk, it is customary to convert the assessed risk value into a risk level, and the risk level is more convenient for online operation risk assessment applications. In order to establish the evaluation standard of a load-loss risk event in online operation risk, the load-loss rate of the node is introduced.
The node load-loss rate is defined as
(6)
where Ki is the ith node load loss ratio.
Point 4: In the conclusion section, the authors should underline in a quantitative manner the paper added value to the field relative to the actual research stage of the field.
Response 4:
In this paper, the CNN is introduced into the online operation risk assessment of power systems, and an online operation risk assessment of the wind power system of the convolution neural network considering multiple random factors is proposed. By analyzing multiple random factors of online risk assessment of the wind power system, and extracting uncertain wind power output data, load fluctuations data, frequent changes in operation patterns, and electrical equipment failure rate data, combined with the expected target of online operation risk assessment, we built sample data for CNN training. After the CNN algorithm is used for offline training, the optimal online operation risk assessment model of the wind power system was obtained. Finally, the trained evaluation model was applied to the online real-time monitoring system data, and the results of the rapid and accurate online operation risk assessment were obtained. The model presented in this paper was verified by simulation by the standard network of 39 nodes of 10 machines of the New England system. The online risk assessment results of the CNN model simulation are the same as the results of the conventional evaluation model. For example, for the first dispatch time, the CNN model risk assessment value is 0.6104, which means the risk rating is IV and the conventional model value is 1, which means that the risk rating is IV; the application of the CNN model simulation time is 0.181 s, which is very short, and far less than the simulation time of the conventional evaluation model, for which the time is 297.315 s. The case studies indicate the following: 1) The CNN model is more accurate when considering multiple random factors, such as the wind power output uncertainty, load fluctuation, operation pattern change, and the electrical equipment failure rate, when compared to considering a single factor causing the operation risk model; 2) the online operation risk assessment model of the wind power system uses the CNN for training implementation. The establishment of this assessment model is implemented in a data-driven manner instead of using the traditional physical assessment model, thus avoiding the process of establishing a complex physical assessment model and avoiding the simplification of multiple random factors. The original information of multiple random factors is preserved to ensure the accuracy of the model. The online operation risk assessment model of the wind power system presented in this paper adopts the CNN method, offline training sample data, and an online application training model. It is proved that the online operation risk assessment model is more rapid and suitable for online application.
In this paper, the evaluation model is more accurate and faster than the traditional online risk assessment model, but the application of the CNN in other aspects and the deeper algorithm of the CNN need to be studied further.
Point 5: English is to be revised throughout the paper
Response 5: the manuscript checked by a professional English editing service.
Author Response File: Author Response.pdf
