Abstract
Accurate risk calculation is beneficial to improve the accuracy of risk identification, which plays a crucial role in auditing in smart grid enterprises. With the development of smart grid, electric utilities have accumulated vast amount of data, big data which has low correlation with risk can cumulative effect on risk and the indicators that affect risk have multiple attributes. In view of above problem, in this paper, a two-layer neural network model is proposed, which inputs the multi-attribute of indicators and the full-scale indicators of different degrees of influence into the model. The problems that the accumulation of multi-attribute and multiple low-related factors of the indicators have an effect on risk calculation are solved in the model. This paper also builds a big data audit platform to carry out the intelligent data collection and risk calculate The results of the examples show that the model has higher accuracy of risk calculation.
Highlights
The risk runs through the whole process of auditing
This paper proposes a two-layer neural network model, considering the impact of the multi-attribute of indicators and the accumulation of multiple low-relevance indicators to solve the problem of inaccurate calculation of risk values which is caused by ignored low correlation factors
Compared with the non-fullscale multi-attribute AHP model and the non-full-scale multiattribute two-layer neural network model, neural network model is better than linear model because there is non-linear relationship between indicators and risk. the Figure 4 shows that the sum error of model is convergence
Summary
The risk runs through the whole process of auditing. Accurate risk identification is conducive to comprehensive control of power grid risks, improving audit quality in the power grid, and playing an important role in enhancing the economic management of the power grid and achieving economic goals [1]. This paper proposes a two-layer neural network model, considering the impact of the multi-attribute of indicators and the accumulation of multiple low-relevance indicators to solve the problem of inaccurate calculation of risk values which is caused by ignored low correlation factors. C. DATA COLLECTION AND PROCESSING The original indicators information of the power grid enterprise business can be collected from intelligent audit platform. The second layer of neural network deals with the influence of the accumulation of a large number of low-related factors on the risk It consists of an input layer, a hidden layer, and an output layer. The input of the second layer are the results of nonlinear processed multi-attributes of indicators which including a large number of low-related factors in first layer. Where Wh(t) denotes the connected weight of the h-th hidden unit to the output layer, and W1h(t), W2h(t), W3h(t) denote the connection weights of the 1-st, 2-ed, 3-th input units to the hth hidden neuron. θh denotes the bias of the hidden neuron h, and θ denotes the bias of output layer. hih(t) denotes the input of the h-th hidden neuron, hoh (t) denotes the output of the h-th hidden neuron. yi(t) denotes the input of the output layer, and yo(t) denotes the output of the output layer. p is the number of neurons in the hidden layer, f is the activation function, and the model uses the Sigmoid function
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
