Method and system for evaluating reliability of integrated energy system

Abstract

The invention discloses an integrated energy system operation reliability evaluation method and system, and the method comprises the steps: determining key nodes in an integrated energy system through employing the sensitive factor indexes of each electrical node for the electricity price in each time period, and determining key elements from the key nodes through employing the operation parameters of each electrical node; obtaining an electric quantity response curve of the key elements after the implementation of the peak-valley time-of-use electricity price, determining the load rates of the key elements in different time periods, and correcting the fault rate of the key elements to obtain a time-varying fault rate; establishing an operation reliability evaluation model of the integrated energy system; determining the fault time of the key element based on the time-varying fault rate, and determining the repair time of the key element based on the repair rate; the operation reliability evaluation model takes different operation states of the integrated energy system and the fault time and the repair time of each key element in each operation state as input data, and the operation reliability evaluation model outputs an operation reliability index to realize reliability evaluation in response to system load change.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system reliability assessment, and in particular, relates to an efficient assessment method and system for the operational reliability of an integrated energy system based on demand response and time-varying characteristics of component failure rate. Background Art

[0002] As the contradiction between energy demand growth and energy shortage continues to intensify, the electricity-gas integrated energy system (EGIES) has become an important form of future energy. Demand response enhances the interaction between users and energy systems, but it also introduces uncertainty in the response to price signals, such as price sensitivity and volatility of load transfer rates, which poses new challenges to system operation. Therefore, conducting EGIES reliability assessment is crucial to ensure its safe and stable operation.

[0003] In the existing technology, medium- and long-term reliability assessment is based on statistical averages, without considering the impact of system operating status and real-time load changes, which limits its guiding value for system risk control. Operational reliability assessment quantifies the impact of environmental conditions on component reliability in real time. However, the complexity of EGIES and multi-energy flow optimization significantly increase the computational burden. In particular, the time-varying characteristics of component reliability parameters and the uncertainty associated with different loads make it a key challenge to accelerate operational reliability assessment and design methods that meet timeliness requirements. The existing technology proposes improvement strategies through state enumeration, Monte Carlo simulation and other methods, including improved sampling, state reduction, model simplification, etc., to reduce computational complexity and improve efficiency. However, these methods still require repeated evaluation when the load changes, which makes it difficult to meet the EGIES "hourly" evaluation requirements. Data-driven rapid reliability assessment methods improve efficiency, but are limited by high training costs and insufficient model generalization capabilities. Hybrid methods that combine analytical methods with data-driven methods also face limitations because they do not conform to the actual situation of EGIES.

[0004] Moreover, in the prior art, the existing improved algorithms have difficulty in handling the multi-dimensional uncertainties in the operation of the electric-gas integrated energy system, especially the need for rapid evaluation as the load changes. This makes it difficult for these methods to meet the real-time or "hourly level" evaluation requirements of system operation. Although data-driven methods have certain efficiency improvements in rapid reliability assessment, they still have limitations due to the high dimensionality of samples and insufficient model generalization capabilities, and cannot cope well with the processing of large-scale data in complex systems. Simplified time-varying models are usually used, ignoring the time-varying characteristics of the failure rate of key components and the impact of demand response, and cannot accurately reflect the changes in component performance over time in actual systems. Summary of the invention

[0005] In order to address the deficiencies in the prior art, the present invention provides a method and system for evaluating the operation reliability of an integrated energy system based on demand response and the time-varying characteristics of component failure rate. Key components are selected based on price sensitivity indicators, and the reliability of the selected key components is evaluated to improve the system's operating efficiency and its ability to cope with load changes. A reliability evaluation method based on the time-varying characteristics of failure rate, especially a hybrid model data-driven method, is used to quickly update the system's reliability index in combination with component operating conditions and price sensitivity. A least squares support vector machine is introduced to model the relationship between system load and reliability, so as to achieve reliability evaluation that quickly responds to system load changes.

[0006] The present invention adopts the following technical solution.

[0007] The present invention proposes a method for evaluating the operation reliability of an integrated energy system, comprising:

[0008] Establish the sensitivity factor index of each electrical node in the comprehensive energy system to the electricity price in each time period; use the sensitivity factor index of each electrical node to the electricity price in each time period to determine the key nodes in the comprehensive energy system, and use the operating parameters of each electrical node to determine the key components from the key nodes;

[0009] Obtain the power response curve of key components after implementing the peak-valley time-of-use electricity price; determine the load rate of each key component in different time periods based on the power response curve of the key components, and use the load rate of each key component in different time periods to correct the failure rate of the key components to obtain the time-varying failure rate;

[0010] Establish an operational reliability assessment model for an integrated energy system; determine the failure time of key components based on the time-varying failure rate, and determine the repair time of key components based on the repair rate; the operational reliability assessment model uses the different operating states of the integrated energy system, as well as the failure time and repair time of each key component under each operating state as input data, and the operational reliability assessment model outputs operational reliability indicators.

[0011] Preferably, the correlation coefficient between the change in electricity price in each time period and the change in electricity quantity of each electrical node is obtained to construct the electricity price weight of each electrical node, and the weighted sum of the electricity price weight of each electrical node and the electricity price in each time period is used as the sensitive factor index of the electrical node to the electricity price in each time period, satisfying the following relationship:

[0012]

[0013] In the formula, γ e (k) is the sensitivity factor index of the electrical node to the electricity price in the kth period, are the total number of power generation nodes and the total number of load nodes in the power system, They are the power generation nodes g e , load node L e The correlation coefficient between the change in electricity volume and the change in electricity price in the kth period, f(λ,k) is the electricity price λ in the kth period e The fitting function of are the power generation node g caused by the electricity price fluctuation in the kth period e , load node L e The change in charge, Δλ e (k) is the change in electricity price in the kth period.

[0014] Preferably, the key nodes in the integrated energy system are determined using the sensitivity factor index of each electrical node to the electricity price in each time period, and the key elements are determined from the key nodes using the operating parameters of each electrical node, including:

[0015] The average value of the sensitivity factor index of each electrical node to electricity price in each time period is used as the risk factor index of each electrical node, and the risk factor index of each electrical node is ranked from large to small, and the electrical nodes ranked in the top 15% are regarded as key electrical nodes; the load conditions of the generators connected to the key electrical nodes are obtained, and the generators under light load or heavy load are regarded as key power supply components; the transmission lines between the key electrical nodes are obtained, and the transmission lines with an operating time of more than 20 years are regarded as key transmission components.

[0016] Preferably, obtaining the power response curve of key components after implementing the peak-valley time-of-use electricity price includes:

[0017] Obtain the rate of change of electricity demand and electricity price in each time period; take the ratio of the rate of change of electricity demand in the current time period to the rate of change of electricity price in the current time period as the self-elasticity coefficient of electricity price in each time period; take the ratio of the rate of change of electricity demand in the current time period to the change of electricity price in non-current time periods as the cross-elasticity coefficient of electricity price in each time period; construct the electricity price elasticity matrix using the self-elasticity coefficient of electricity price and the cross-elasticity coefficient of electricity price;

[0018] Among them, after the implementation of peak-valley time-of-use electricity prices, the price elasticity matrix represents the rate of change of electricity demand and the rate of change of electricity prices, which satisfies the following relationship:

[0019]

[0020] In the formula, Q p , Q m , Q v are the electricity demand during peak hours, flat hours and off-peak hours, ΔQ p , ΔQ m , ΔQ v are the changes in power demand during peak hours, flat hours, and valley hours, respectively,p , m , v are the electricity prices during peak hours, flat hours and off-peak hours, respectively, Δλ p , Δλ m , Δλ v are the electricity price changes during peak hours, flat hours, and valley hours, respectively. 11 、E 22 、E 33 is the electricity price elasticity coefficient, E 12 、E 13 、E 21 、E 23 、E 31 、E 32 is the cross elasticity coefficient of electricity price, E is the electricity price elasticity matrix;

[0021] Based on the load forecast curve and using the electricity price elasticity matrix, the electricity response curve after implementing the peak and valley time-of-use electricity price is determined to meet the following relationship:

[0022]

[0023] Where L(t) is the electricity response curve after the implementation of peak-valley time-of-use electricity prices, ΔT is the duration vector of each period, E is the electricity price elasticity matrix, Δλ is the electricity price change rate vector, and L 0 (t) is the load prediction curve.

[0024] Preferably, the load rate of each key component in different time periods is determined based on the power response curve of the key component, and the failure rate of the key component is corrected by using the load rate of each key component in different time periods to obtain the time-varying failure rate, including:

[0025] For key power supply components, the historical failure rate and historical load rate of the key power supply components are fitted, and Gaussian noise is introduced during the fitting to determine the relationship curve between the failure rate and the load rate of the key power supply components; the load rate of the key power supply components in different time periods is determined based on the power response curve of the key power supply components, and the time-varying failure rate of the key power supply components is determined from the relationship curve between the failure rate and the load rate using the load rate in different time periods determined;

[0026] For key transmission components, the load current values ​​of the key transmission components in different time periods are determined based on the power response curves of the key transmission components, and the time-varying failure rate of the key transmission components is calculated using the following relationship:

[0027]

[0028] In the formula, is the time-varying failure rate of the key transmission components at time t, I 1,I 2 are the rated current value and current protection action setting value of the key transmission components, respectively; I is the load current value of the key transmission components in different time periods, is the maximum value of the historical failure rate of key transmission components, The service failure rate of key power transmission components;

[0029] Among them, the service failure rate of key transmission components satisfies the following relationship:

[0030]

[0031] In the formula, is the basic failure rate of key transmission components, T 0 is the service life of the key transmission component, i is the number of the time period, Δt is the interval between each time period, and f(t) is the probability distribution function of the impact of the aging effect of the key transmission component on the failure rate.

[0032] Preferably, determining the failure time of a key component based on the time-varying failure rate and determining the repair time of a key component based on the repair rate comprises:

[0033] According to the time-varying failure rate and repair rate, the probability density function of the failure time and repair time of key components obeying the exponential distribution is established, which satisfies the following relationship:

[0034] f failure (t) = χe -χt

[0035] f repair (t) = μe -μt

[0036] In the formula, f failure (t) is the probability density function of the failure time of key components following exponential distribution, f repair (t) is the probability density function of the repair time of the key component obeying the exponential distribution, χ is the time-varying failure rate of the key component, and μ is the repair rate of the key component.

[0037] Preferably, under different operation state timing vectors, the failure time of the key component is randomly generated according to the probability density function that the failure time of the key component obeys the exponential distribution, and the repair time of the key component is randomly generated according to the probability density function that the repair time of the key component obeys the exponential distribution; different operation state timing vectors, and the failure time and repair time under each operation state timing vector constitute the input data of the operation reliability evaluation model;

[0038] Among them, the operating state time series vector of the integrated energy system satisfies the following relationship:

[0039] S(t)=[S1 (t),S 2 (t),…,S i (t),…,S N (t)]

[0040] Where S(t) is the operating state time series vector of the key components, S i (t) is the operating state of the i-th key component at time t, S i (t) = 1 means that the i-th key component is in working state at time t, S i (t)=0 indicates that the i-th key component is in a faulty state at time t, and N is the number of key components.

[0041] Preferably, the operation reliability evaluation model uses input data to perform iterative operations and outputs an operation reliability index; the specific process is as follows:

[0042] 1) Initialization

[0043] Set the total length of the iteration operation time T sim and the iteration operation time step Δτ; at the beginning of the iteration operation, all key components are set to be in working state as the initial value of the system operation state timing vector, and the failure time T of each key component under the initial value of the system operation state timing vector is determined failure and repair time T repair ;

[0044] 2) Iterative update of input data

[0045] Starting from the iteration time τ = 0, within each iteration time step Δτ, for each key component, if the iteration time τ reaches the failure time T failure , the key component enters the fault state, and the system operation state timing vector is updated at this time, and the updated system operation state timing vector and its corresponding fault time T of each key component are determined failure and repair time T repair As the input data of τ+Δτ; if the iterative operation time τ reaches the repair time T repair , the key components are restored to the working state, and the system operation state timing vector is updated at this time, and the updated system operation state timing vector and its corresponding failure time T of each key component are determined failure and repair time T repair As input data of τ+Δτ;

[0046] 3) Within each iterative operation time step Δτ, determine whether a load loss event occurs;

[0047] Determine whether a load loss event occurs within the iterative calculation time step Δτ. If a load loss event occurs, record the load loss amount caused by the load loss event and the duration of the load loss event.

[0048] 4) Using the recorded load loss amount and load loss duration, calculate the load loss probability and expected power outage of the integrated energy system; including:

[0049] The probability of load loss satisfies the following relationship:

[0050]

[0051] Where LOLP is the load loss probability of the integrated energy system, T LO is the cumulative value of the duration of each load loss in the comprehensive energy system during the iterative calculation process, T total is the total duration of the iterative operation;

[0052] The expected unpowered power supply satisfies the following relationship:

[0053]

[0054] Where EENS is the expected unpowered energy of the integrated energy system, N LO is the total number of load loss events in the integrated energy system during the iterative calculation process, L ch,i is the load loss caused by the i-th load loss event, t LO,i is the duration of the i-th load loss event.

[0055] Preferably, an operation reliability assessment model of the integrated energy system is established based on a least squares support vector machine classifier.

[0056] The present invention also proposes a comprehensive energy system operation reliability assessment system, comprising:

[0057] The key component selection module is used to establish the sensitivity factor index of each electrical node in the integrated energy system to the electricity price in each time period; determine the key nodes in the integrated energy system using the sensitivity factor index of each electrical node to the electricity price in each time period, and determine the key components from the key nodes using the operating parameters of each electrical node;

[0058] The time-varying failure rate calculation module is used to obtain the power response curve of the key components after the implementation of the peak-valley time-of-use electricity price; based on the power response curve of the key components, the load rate of each key component in different time periods is determined, and the failure rate of the key components is corrected by using the load rate of each key component in different time periods to obtain the time-varying failure rate;

[0059] The operation reliability assessment module is used to establish an operation reliability assessment model for the integrated energy system; determine the failure time of key components based on the time-varying failure rate, and determine the repair time of key components based on the repair rate; the operation reliability assessment model uses the different operating states of the integrated energy system, as well as the failure time and repair time of each key component under each operating state as input data, and the operation reliability assessment model outputs an operation reliability index.

[0060] The present invention is also a terminal, comprising a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the method.

[0061] The present invention is also a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method when executed by a processor.

[0062] The beneficial effects of the present invention are that, compared with the prior art, at least the method proposed in the present invention determines the time-varying failure rate, quantifies the failure rate of components at different time points, accurately reflects the actual operating status conditions of key components, and combines the load demand response caused by electricity price fluctuations to achieve accurate evaluation of operating reliability.

[0063] The method proposed in the present invention can optimize the relationship between load level and system stability, more effectively deal with the complexity and uncertainty in the electrical integrated energy system, improve the safety and stability of the system, quickly evaluate the operational reliability of the system, reduce the computational complexity caused by high-dimensional samples, and improve the computational efficiency and accuracy of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a flow chart of the comprehensive energy system operation reliability assessment method proposed by the present invention;

[0065] Figure 2 is a curve showing the relationship between the failure rate and the load rate of the key power supply components in the embodiment of the present invention;

[0066] Figure 3 is a curve showing the variation of the failure rate of key power transmission components with the service time and load current in an embodiment of the present invention;

[0067] Figure 4 is a schematic diagram of load change curve and electricity price distribution before and after demand response in an embodiment of the present invention;

[0068] Figure 5 It is the comparison result of EENS and EGNS of the model data hybrid drive and the model drive and data drive proposed in the present invention; wherein EENS is the expected unpowered amount, and EGNS is the expected maximum unpowered amount;

[0069] Figure 6This is a comparison of the EENS errors of the model data hybrid drive and data drive proposed in the present invention. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only embodiments of a part of the present invention, rather than all embodiments. Based on the spirit of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the protection scope of the present invention.

[0071] This paper proposes a comprehensive energy system operation reliability evaluation method based on demand response and time-varying characteristics of component failure rate, such as Figure 1 As shown, including:

[0072] Step 1: Establish a sensitivity factor index of each electrical node in the integrated energy system to electricity price; determine the key nodes in the integrated energy system using the sensitivity factor index of each electrical node to electricity price and the operating parameters of each electrical node;

[0073] Specifically, step 1 includes:

[0074] Step 1.1, obtain the correlation coefficient between the change in electricity price in each time period and the change in electricity quantity of each electrical node to construct the electricity price weight of each electrical node, and use the weighted sum of the electricity price weight of each electrical node and the electricity price in each time period as the sensitive factor indicator of the electrical node to the electricity price in each time period.

[0075] The integrated energy system is an electricity-gas integrated energy system (EGIES). In the framework of electricity price demand response, the sensitivity of electricity price fluctuations can be used as a basis for measuring the importance of energy transmission components in the system. Specifically, the importance of energy transmission components can be determined by their degree of response to load changes caused by electricity price fluctuations. For power systems, especially under high or low electricity price conditions, key components in the system will respond quickly to load transfer and demand response caused by electricity price fluctuations. Therefore, by weighting the flexibility of these components in the demand response process and their impact on the economic cost of the system, the sensitivity factor index of electrical nodes to electricity prices in each time period satisfies the following relationship:

[0076]

[0077] In the formula, γ e (k) is the sensitivity factor index of the EGIES electrical node to the electricity price in the kth period, are the total number of power generation nodes and the total number of load nodes in the power system, They are the power generation nodes g e , load node L e The correlation coefficient between the change in electricity volume and the change in electricity price in the kth period, f(λ,k) is the electricity price λ in the kth period e The fitting function of are the power generation node g caused by the electricity price fluctuation in the kth period e , load node L e The change in charge, Δλ e (k) is the change in electricity price in the kth period.

[0078] Step 1.2, take the average value of the sensitivity factor index of each electrical node to electricity price in each time period as the risk factor index of each electrical node, sort the risk factor index of each electrical node from large to small, and take the electrical nodes ranked in the top 15% as the key electrical nodes; obtain the load conditions of the generators connected to the key electrical nodes, and take the generators under light load or heavy load as the key power supply components; obtain the transmission lines between the key electrical nodes, and take the transmission lines with an operating time of more than 20 years as the key transmission components.

[0079] The key nodes and key components determined by the present invention are highly sensitive to changes in electricity prices. The reliability indicators of key components with high sensitivity to changes in electricity prices will also be different in different time periods. Therefore, the reliability indicators in a certain time period or state cannot be used as the basis for reliability evaluation. Instead, the changes in the reliability indicators of these components under the influence of time-varying electricity prices should be fully considered.

[0080] Step 2, obtaining the power response curve of the key components after the implementation of the peak-valley time-of-use electricity price; determining the load rate of each key component in different time periods based on the power response curve of the key components, and using the load rate of each key component in different time periods to correct the failure rate of the key components to obtain the time-varying failure rate.

[0081] Specifically, step 2 includes:

[0082] Step 2.1, obtain the rate of change of electricity demand and the rate of change of electricity price in each time period; use the ratio of the rate of change of electricity demand in the current time period to the rate of change of electricity price in the current time period as the self-elasticity coefficient of electricity price in each time period; use the ratio of the rate of change of electricity demand in the current time period to the change of electricity price in non-current time periods as the cross-elasticity coefficient of electricity price in each time period; construct the electricity price elasticity matrix using the self-elasticity coefficient of electricity price and the cross-elasticity coefficient of electricity price.

[0083] In the embodiment, the evaluation period is divided into a peak period, a flat period and a valley period according to the peak and valley time-of-use electricity price;

[0084] Demand response based on electricity prices mainly forms a reasonable electricity consumption orientation for users by introducing peak and valley time-of-use electricity prices, thereby achieving peak shaving and valley filling of the load curve, improving the load characteristics of the network, and thus improving the reliability level of the system.

[0085] After implementing the peak-valley time-of-use electricity price, the price elasticity matrix represents the rate of change of electricity demand and the rate of change of electricity price, as shown below:

[0086]

[0087] In the formula, Q p , Q m , Q v are the electricity demand during peak hours, flat hours and off-peak hours, ΔQ p , ΔQ m , ΔQ v are the changes in power demand during peak hours, flat hours, and valley hours, respectively, p , m , v are the electricity prices during peak hours, flat hours and off-peak hours, respectively, Δλ p , Δλ m , Δλ v are the electricity price changes during peak hours, flat hours, and valley hours, respectively. 11 、E 22 、E 33 is the electricity price elasticity coefficient, E 12 、E 13 、E 21 、E 23 、E 31 、E 32 is the cross elasticity coefficient of electricity price, and E is the electricity price elasticity matrix.

[0088] Step 2.2, based on the load forecast curve, using the electricity price elasticity matrix, determine the power response curve of key components after implementing the peak and valley time-of-use electricity price;

[0089] Based on the user's demand for load at different time periods during the day, the distribution company has formulated a time-of-use electricity price policy, dividing the electricity price into three periods: peak, flat and valley, to encourage users to change their electricity consumption behavior. According to the electricity price information, users can transfer loads when the electricity price is peak and transfer loads when the electricity price is low, thereby realizing load transfer, reducing electricity costs and promoting the full utilization of electricity. The load transfer rate refers to the ratio of the load transferred from the high electricity price period to the low electricity price period to the load in the high electricity price period, and has a linear function relationship with the electricity price difference.

[0090] According to the electricity price period, load transfer includes:

[0091] 1) Shifting load from peak electricity prices to normal electricity prices;

[0092] 2) Shifting load from peak electricity prices to valley electricity prices;

[0093] 3) Transfer load from normal electricity prices to off-peak electricity prices.

[0094] The specific power response curves under the above three load transfer situations are as follows:

[0095]

[0096] Where, L 0 (t) is the load forecast curve, L(t) is the power response curve after the implementation of peak and valley time-of-use electricity prices, T p , T m , T v are the peak, flat and valley periods of electricity consumption, respectively, ΔT p , ΔT m , ΔT v are the duration of peak, flat and trough periods respectively.

[0097] After implementing the peak-valley time-of-use electricity price, the power response curve of key components satisfies the following relationship:

[0098]

[0099] Where L(t) is the power response curve of key components after the implementation of peak-valley time-of-use electricity prices, ΔT is the duration vector of each period, E is the electricity price elasticity matrix, Δλ is the electricity price change rate vector, and L 0 (t) is the load prediction curve.

[0100] Step 2.3, determining the load rate of each key component at different time periods based on the power response curve of the key component, and using the load rate of each key component at different time periods to correct the failure rate of the key component to obtain the time-varying failure rate;

[0101] The electricity response curve of key components after implementing peak-valley time-of-use electricity prices proposed in the present invention is based on the load forecast curve and introduces an electricity price elasticity matrix to characterize the response to electricity price fluctuations. Key components are sensitive to electricity prices, so the electricity response curve can reflect the load rate of key components in each time period, and the failure rate of equipment is mainly affected by the load rate.

[0102] Specifically, for key power supply components, the historical failure rate and the historical load rate of the key power supply components are fitted, and Gaussian noise is introduced during the fitting to determine the relationship curve between the failure rate and the load rate of the key power supply components; the load rate of the key power supply components in different time periods is determined based on the power response curve of the key power supply components, and the time-varying failure rate of the key power supply components is determined from the relationship curve between the failure rate and the load rate using the determined load rate in different time periods;

[0103] For key power supply components, historical operation data is fitted to establish the relationship curve between the failure rate and load rate of key power supply components, such as Figure 2 As shown in the figure, when the load rate decreases and increases, the failure rate also increases. The load rate under low load is set to L low =0.15, the load rate under heavy load is L high =0.95. In addition, Figure 2 Gaussian noise is also introduced in the simulation to make the failure rate and load rate curve show random fluctuations, simulating the uncertainty of failure rate caused by factors such as environment and material fatigue in actual systems.

[0104] For key transmission components, the load current values ​​of the key transmission components in different time periods are determined based on the power response curves of the key transmission components, and the time-varying failure rate of the key transmission components is calculated using the following relationship:

[0105]

[0106] In the formula, is the time-varying failure rate of the key transmission components at time t, I 1 ,I 2 are the rated current value and current protection action setting value of the key transmission components, respectively; I is the load current value of the key transmission components in different time periods, is the maximum value of the historical failure rate of key transmission components, The service failure rate of key power transmission components;

[0107] For the transmission lines on EGIES, the influence of load current I on the failure rate of transmission lines should be considered. Therefore, the load current values ​​of key transmission components in different time periods are determined based on the power response curves of key transmission components, so as to correct the failure rate.

[0108] The failure rate of transmission lines is affected by service time and load rate and presents a time-varying characteristic. As the load current increases, the heat generated by the transmission line increases, and the mechanical strength gradually decreases, resulting in an increase in the line failure rate. Considering the impact of aging effects on line failure rates, the service failure rate of key transmission components satisfies the following relationship:

[0109]

[0110] In the formula, is the basic failure rate of key transmission components, T 0 is the service life of the key transmission component, i is the number of the time period, Δt is the interval between each time period, and f(t) is the probability distribution function of the impact of the aging effect of the key transmission component on the failure rate;

[0111] Among them, the basic failure rate of key transmission components satisfies the following relationship:

[0112]

[0113] Where ζ is the unavailability rate of key transmission components, and μ is the repair rate of key transmission components, both of which are historical statistical data.

[0114] Figure 3 The variation of the failure rate of the transmission line with the service time and load current in the embodiment is given.

[0115] The present invention introduces the time-varying characteristics of component failure rate in the operational reliability assessment, which can more accurately reflect the operating status of the component under different load conditions and improve the accuracy of reliability assessment.

[0116] Step 3, establish an operation reliability evaluation model for the integrated energy system; determine the failure time of key components based on the time-varying failure rate, and determine the repair time of key components based on the repair rate; the operation reliability evaluation model takes the different operation states of the integrated energy system, as well as the failure time and repair time of each key component under each operation state as input data, and the operation reliability evaluation model outputs an operation reliability index.

[0117] Specifically, step 3 includes:

[0118] Step 3.1, establish an operation reliability assessment model of the integrated energy system based on the least squares support vector machine classifier (LSSVM);

[0119] Compared with the traditional model-driven method, the model-data hybrid driven method can respond quickly when the load changes, and establish the mapping relationship between the load level and the reliability index through the LSSVM (least squares support vector machine) model to achieve rapid update. This not only improves the computing efficiency, but also reduces the computing burden of repeated evaluation due to load fluctuations.

[0120] Among them, the hybrid driving method of EGIES operation reliability assessment taking into account demand response is as follows:

[0121] LSSVM is an improvement of SVM with excellent generalization ability and good training effect on small samples. It is suitable for IES reliability assessment scenarios where the cost of obtaining training samples is high.

[0122] Assume that the training sample set is {(x i ,y i ),i=1,2,…,N S}, x i ∈R n is the input data, y i ∈R n is the output data, N S is the total number of training samples. LSSVM uses the principle of structural risk minimization of the sample set to establish a regression model:

[0123]

[0124] Where J(·) is the loss function, e error,i is the training error of the ith training sample, For the input data x i From the original space R n The nonlinear mapping function to the high-dimensional feature space H, ω is the weight, b is the bias, γ is the regularization parameter, e error is the set of training errors of the training samples.

[0125] Introducing the Lagrange multiplier α i Solved by Lagrangian method, the LSSVM regression model is:

[0126]

[0127] Where f(x) is the transfer function of the LSSVM regression model, b M is the model parameter, K(x i ,x j ) is the RBF kernel function, as shown in the following formula:

[0128]

[0129] In the formula, x i 、x j are all input data, and σ is the kernel function parameter.

[0130] In the least squares support vector machine classifier (LSSVM) modeling process, the regularization parameter γ and the kernel function parameter σ have a great influence on the model accuracy. The present invention uses the parameter search function in the MATLAB LS-SVM lab toolbox to determine these two parameters.

[0131] By introducing the least squares support vector machine, the present invention can quickly update the system's operational reliability, especially when the load fluctuates. Compared with the traditional long-term evaluation method based on statistical average, it has higher real-time performance and can better meet the needs of the integrated energy system for "hourly" evaluation.

[0132] The present invention proposes a hybrid model data-driven method. Compared with the traditional single model-driven method, the present invention greatly reduces the computational complexity and can quickly perform reliability assessment, especially when the load changes frequently, significantly reducing the calculation time.

[0133] Step 3.2, determine the failure time of key components based on the time-varying failure rate, and determine the repair time of key components based on the repair rate; the operation reliability assessment model takes different operating states of the integrated energy system, and the failure time and repair time of each key component under each operating state as input data;

[0134] Sequential Monte Carlo simulation is a time-driven stochastic simulation method suitable for reliability assessment of systems during dynamic failure and repair processes. By simulating the random failure and repair behavior of components at each time step, the time evolution of the system can be captured, thereby evaluating the long-term operational reliability of the system.

[0135] Specifically, based on the time-varying failure rate and repair rate, a probability density function of the failure time and repair time of key components that obey an exponential distribution is established, satisfying the following relationship:

[0136] f failure (t) = χe -χt

[0137] f repair (t) = μe -μt

[0138] In the formula, f failure (t) is the probability density function of the failure time of key components following exponential distribution, f repair (t) is the probability density function of the repair time of the key component following the exponential distribution, χ is the time-varying failure rate of the key component, and μ is the repair rate of the key component;

[0139] The state of the integrated energy system is determined by the working state (working or faulty) of each key component. Assume that the state quantity of each key component is 1 when it is in working state and 0 when it is in faulty state. Then the operating state time series vector of the integrated energy system satisfies the following relationship:

[0140] S(t)=[S 1 (t),S 2 (t),…,S i (t),…,SN (t)]

[0141] Where S(t) is the operating state time series vector of the key components, S i (t) is the operating state of the i-th key component at time t, S i (t) = 1 means that the i-th key component is in working state at time t, S i (t)=0 indicates that the i-th key component is in a faulty state at time t, and N is the number of key components.

[0142] Under different state time series vectors, the failure time of key components is randomly generated according to the probability density function that the failure time of key components obeys the exponential distribution, and the repair time of key components is randomly generated according to the probability density function that the repair time of key components obeys the exponential distribution; different state time series vectors, and the failure time and repair time under each state time series vector constitute the input data of the operation reliability evaluation model;

[0143] The existing technology usually performs reliability assessment based on a fixed failure rate, while ignoring the uncertainty of load response under electricity price fluctuations and the dynamic impact of changes in system operating status on the failure rate, which may lead to lag and insufficient accuracy in reliability assessment. Therefore, the present invention considers the time-varying characteristics of the failure rate, not only combines the changes in the operating status of the integrated energy system, but also introduces the change in load rate to characterize price sensitivity, thereby dynamically adjusting the failure rate, so that the reliability assessment is more in line with the dynamic characteristics of the actual system.

[0144] Step 3.3, the operation reliability assessment model uses the input data to perform iterative calculations and outputs operation reliability indicators, including load loss probability and expected unpowered power. The specific process is as follows:

[0145] 1) Initialization

[0146] Set the total length of the iteration operation time T sim and the iteration operation time step Δτ; at the beginning of the iteration operation, all key components are set to be in working state as the initial value of the system operation state timing vector, and the failure time T of each key component under the initial value of the system operation state timing vector is determined failure and repair time T repair ;

[0147] 2) Iterative update of input data

[0148] Starting from the iteration time τ = 0, the system time is gradually advanced within each iteration time step Δτ: for each key component, if the iteration time τ reaches the failure time T failure, the key component enters the fault state, and the system operation state timing vector is updated at this time, and the updated system operation state timing vector and its corresponding fault time T of each key component are determined failure and repair time T repair As the input data of τ+Δτ; if the iterative operation time τ reaches the repair time T repair , the key components are restored to the working state, and the system operation state timing vector is updated at this time, and the updated system operation state timing vector and its corresponding failure time T of each key component are determined failure and repair time T repair As input data of τ+Δτ;

[0149] 4) Within each iterative operation time step Δτ, determine whether a load loss event occurs;

[0150] If some component failures cause the system to be unable to meet the user's electricity or gas needs, determine whether a load loss event occurs within the iterative calculation time step Δτ. If a load loss event occurs, record the load loss amount caused by the load loss event and the duration of the load loss event.

[0151] 5) Using the recorded load loss amount and load loss duration, calculate the load loss probability and expected power failure amount of the integrated energy system;

[0152] During the iterative calculation process, the system may experience multiple load loss events. After the iterative calculation is completed, the load loss probability (LOLP) and expected unpowered energy (EENS) of the integrated energy system are calculated, including:

[0153] The loss of load probability (LOLP) indicates the probability of a system loss of load event occurring within a specific time period, and satisfies the following relationship:

[0154]

[0155] Where LOLP is the load loss probability of the integrated energy system, T LO is the cumulative value of the duration of each load loss in the comprehensive energy system during the iterative calculation process, T total is the total duration of the iterative operation;

[0156] In the embodiment, the value of LOLP is greater than 0 and less than 1, which is the proportion of time when load loss events occur in the system during the iterative operation process. Obviously, the smaller the load loss probability of the integrated energy system, the higher the operational reliability of the integrated energy system.

[0157] The expected unsupplied energy (EENS) represents the amount of energy that does not meet user demand due to system failures within a specific period of time, and satisfies the following relationship:

[0158]

[0159] Where EENS is the expected unpowered energy of the integrated energy system, N LO is the total number of load loss events in the integrated energy system during the iterative calculation process, L ch,i is the load loss caused by the i-th load loss event, t LO,i is the duration of the i-th load loss event.

[0160] The present invention also proposes a comprehensive energy system operation reliability assessment system, comprising:

[0161] The key component selection module is used to establish the sensitivity factor index of each electrical node in the integrated energy system to the electricity price in each time period; determine the key nodes in the integrated energy system using the sensitivity factor index of each electrical node to the electricity price in each time period, and determine the key components from the key nodes using the operating parameters of each electrical node;

[0162] The time-varying failure rate calculation module is used to obtain the power response curve of the key components after the implementation of the peak-valley time-of-use electricity price; based on the power response curve of the key components, the load rate of each key component in different time periods is determined, and the failure rate of the key components is corrected by using the load rate of each key component in different time periods to obtain the time-varying failure rate;

[0163] The operation reliability assessment module is used to establish an operation reliability assessment model for the integrated energy system; determine the failure time of key components based on the time-varying failure rate, and determine the repair time of key components based on the repair rate; the operation reliability assessment model uses the different operating states of the integrated energy system, as well as the failure time and repair time of each key component under each operating state as input data, and the operation reliability assessment model outputs an operation reliability index.

[0164] The example is set up based on the IEEE14-NGS10 electric-gas interconnection system. The power system part adopts a modified IEEE14 node power system, including 2 power supply nodes, 20 transmission lines and 11 electric loads, with a peak load of 259MW. The natural gas system part adopts a modified NGS10 node system, including 1 gas source node, 9 gas pipelines and 3 gas loads, with a peak load of 4.32m 3 / s. The energy supply equipment in the system includes a P2G device, a gas unit, a gas source and two conventional units. The calorific value of natural gas is 10kWh / m3. The reliability assessment convergence accuracy is set to 0.03.

[0165] The model is solved in MATLAB based on the typical daily load data and electricity price information before demand response. Figure 4It is the load curve and electricity price distribution information before and after the implementation of demand response. Figure 4 It can be seen that the implementation of demand response by power users can increase the load during the off-peak electricity price period and reduce the load during the peak electricity price period, playing the role of peak shifting and valley filling. According to the established demand response model based on load transfer rate, it can be seen that the power load is transferred from the high electricity price period to the low electricity price period to reduce the user's electricity cost.

[0166] Assume that the load level of the power system and the natural gas system varies in the range of [0.4, 1] under the per-unit value, with a step size of 0.05. A total of 169 load data are generated as input data samples using the grid search method, and the analytical model coefficients are calculated as output data samples using the method proposed in this paper. The LSSVM regression model parameters are trained offline using 169 training sample sets to obtain the LSSVM model of the analytical model coefficients with respect to the system load level. Substitute the system load level into the trained LSSVM model to obtain the analytical model at each time during the system operation day, and then substitute the failure rate of key components into the analytical model to obtain the operation reliability evaluation results, such as Figure 5 shown.

[0167] from Figure 6 It can be seen that the maximum absolute error value of the EENS indicator of the method proposed in the present invention is 4.17%, and the absolute value of the EENS indicator error does not exceed 5%. The absolute value of the error of the EENS indicator in the data-driven evaluation results is basically greater than 5%. These confirm that the hybrid drive method proposed in the present invention significantly improves the accuracy.

[0168] At the same time, the present invention compares the calculation time of the proposed hybrid drive method and the single model drive method, as shown in Table 1. Since the traditional model-driven method needs to repeatedly evaluate the system reliability level in the current period every hour, the calculation complexity is extremely high, and the method proposed in this chapter can achieve real-time update of EGIES operation reliability indicators by establishing a model-data hybrid drive model offline.

[0169] Table 1 Comparison of computational time between the proposed method and the single model driven method

[0170]

[0171]

[0172] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0173] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0174] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0175] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0176] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for evaluating the operational reliability of an integrated energy system, characterized in that: include: Establish the sensitivity factor index of each electrical node in the integrated energy system to electricity price in each time period; The key nodes in the integrated energy system are determined by using the sensitive factor index of each electrical node to the electricity price in each time period, and the key components are determined from the key nodes by using the operating parameters of each electrical node; Obtain the power response curve of key components after implementing the peak-valley time-of-use electricity price; determine the load rate of each key component in different time periods based on the power response curve of the key components, and use the load rate of each key component in different time periods to correct the failure rate of the key components to obtain the time-varying failure rate; Establish an operational reliability assessment model for the integrated energy system; determine the failure time of key components based on the time-varying failure rate, and determine the repair time of key components based on the repair rate; The operation reliability assessment model takes the different operation states of the integrated energy system, as well as the failure time and repair time of each key component under each operation state as input data, and outputs the operation reliability index.

2. The method for evaluating the operation reliability of an integrated energy system according to claim 1, characterized in that: The correlation coefficient between the change in electricity price in each period and the change in electricity quantity of each electrical node is obtained to construct the electricity price weight of each electrical node. The weighted sum of the electricity price weight of each electrical node and the electricity price in each period is used as the sensitive factor index of the electrical node to the electricity price in each period, satisfying the following relationship: In the formula, γ e (k) is the sensitivity factor index of the electrical node to the electricity price in the kth period, are the total number of power generation nodes and the total number of load nodes in the power system, They are the power generation nodes g e , load node L e The correlation coefficient between the change in electricity volume and the change in electricity price in the kth period, f(λ,k) is the electricity price λ in the kth period e The fitting function of are the power generation node g caused by the electricity price fluctuation in the kth period e , load node L e The change in charge, Δλ e (k) is the change in electricity price in the kth period.

3. The method for evaluating the operation reliability of an integrated energy system according to claim 2, characterized in that: The key nodes in the integrated energy system are determined by using the sensitive factor index of each electrical node to the electricity price in each period, and the key components are determined from the key nodes by using the operating parameters of each electrical node, including: The average value of the sensitivity factor index of each electrical node to electricity price in each time period is used as the risk factor index of each electrical node, and the risk factor index of each electrical node is ranked from large to small, and the electrical nodes ranked in the top 15% are regarded as key electrical nodes; the load conditions of the generators connected to the key electrical nodes are obtained, and the generators under light load or heavy load are regarded as key power supply components; the transmission lines between the key electrical nodes are obtained, and the transmission lines with an operating time of more than 20 years are regarded as key transmission components.

4. The method for evaluating the operation reliability of an integrated energy system according to claim 3, characterized in that: Obtain the power response curve of key components after implementing peak and valley time-of-use electricity prices, including: Obtain the rate of change of electricity demand and electricity price in each time period; take the ratio of the rate of change of electricity demand in the current time period to the rate of change of electricity price in the current time period as the self-elasticity coefficient of electricity price in each time period; take the ratio of the rate of change of electricity demand in the current time period to the change of electricity price in non-current time periods as the cross-elasticity coefficient of electricity price in each time period; construct the electricity price elasticity matrix using the self-elasticity coefficient of electricity price and the cross-elasticity coefficient of electricity price; Among them, after the implementation of peak-valley time-of-use electricity prices, the price elasticity matrix represents the rate of change of electricity demand and the rate of change of electricity prices, which satisfies the following relationship: In the formula, Q p , Q m , Q v are the electricity demand during peak hours, flat hours and off-peak hours, ΔQ p , ΔQ m , ΔQ v are the changes in power demand during peak hours, flat hours, and valley hours, respectively, p , m , v are the electricity prices during peak hours, flat hours and off-peak hours, respectively, Δλ p , Δλ m , Δλ v are the electricity price changes during peak hours, flat hours, and valley hours, respectively. 11 、E 22 、E 33 is the electricity price elasticity coefficient, E 12 、E 13 、E 21 、E 23 、E 31 、E 32 is the cross elasticity coefficient of electricity price, E is the electricity price elasticity matrix; Based on the load forecast curve and using the electricity price elasticity matrix, the electricity response curve after implementing the peak and valley time-of-use electricity price is determined to meet the following relationship: Where L(t) is the electricity response curve after the implementation of peak-valley time-of-use electricity prices, ΔT is the duration vector of each time period, E is the electricity price elasticity matrix, Δλ is the electricity price change rate vector, and L0(t) is the load forecast curve.

5. The method for evaluating the operation reliability of an integrated energy system according to claim 4, characterized in that: Based on the power response curve of the key components, the load rate of each key component in different time periods is determined, and the failure rate of the key components is corrected by using the load rate of each key component in different time periods to obtain the time-varying failure rate, including: For key power supply components, the historical failure rate and historical load rate of the key power supply components are fitted, and Gaussian noise is introduced during the fitting to determine the relationship curve between the failure rate and the load rate of the key power supply components; the load rate of the key power supply components in different time periods is determined based on the power response curve of the key power supply components, and the time-varying failure rate of the key power supply components is determined from the relationship curve between the failure rate and the load rate using the load rate in different time periods determined; For key transmission components, the load current values ​​of the key transmission components in different time periods are determined based on the power response curves of the key transmission components, and the time-varying failure rate of the key transmission components is calculated using the following relationship: In the formula, is the time-varying failure rate of the key transmission element at time t, I1 and I2 are the rated current value and current protection action setting value of the key transmission element, respectively, and I is the load current value of the key transmission element at different time periods. is the maximum value of the historical failure rate of key transmission components, The service failure rate of key power transmission components; Among them, the service failure rate of key transmission components satisfies the following relationship: In the formula, is the basic failure rate of the key transmission component, T0 is the service life of the key transmission component, i is the number of the time period, Δt is the interval between each time period, and f(t) is the probability distribution function of the influence of the aging effect of the key transmission component on the failure rate.

6. The method for evaluating the operation reliability of an integrated energy system according to claim 1, characterized in that: Determine the failure time of key components based on the time-varying failure rate, and determine the repair time of key components based on the repair rate, including: According to the time-varying failure rate and repair rate, the probability density function of the failure time and repair time of key components obeying the exponential distribution is established, which satisfies the following relationship: f repair (t)=μe -μt In the formula, f failure (t) is the probability density function of the failure time of key components following exponential distribution, f repair (t) is the probability density function of the repair time of the key component obeying the exponential distribution, χ is the time-varying failure rate of the key component, and μ is the repair rate of the key component.

7. The method for evaluating the operation reliability of an integrated energy system according to claim 6, characterized in that: Under different operation state timing vectors, the failure time of key components is randomly generated according to the probability density function that the failure time of key components obeys the exponential distribution, and the repair time of key components is randomly generated according to the probability density function that the repair time of key components obeys the exponential distribution; different operation state timing vectors, and the failure time and repair time under each operation state timing vector constitute the input data of the operation reliability evaluation model; Among them, the operating state time series vector of the integrated energy system satisfies the following relationship: S(t)=[S1(t),S2(t),…,S i (t),…,S N (t)] Where S(t) is the operating state time series vector of the key components, S i (t) is the operating state of the i-th key component at time t, S i (t) = 1 means that the i-th key component is in working state at time t, S i (t)=0 indicates that the i-th key component is in a faulty state at time t, and N is the number of key components.

8. The method for evaluating the operation reliability of an integrated energy system according to claim 7, characterized in that: The operation reliability evaluation model uses input data for iterative calculations and outputs operation reliability indicators. The specific process is as follows: 1) Initialization Set the total length of the iteration operation time T sim and the iteration operation time step Δτ; at the beginning of the iteration operation, all key components are set to be in working state as the initial value of the system operation state timing vector, and the failure time T of each key component under the initial value of the system operation state timing vector is determined failure and repair time T repair ; 2) Iterative update of input data Starting from the iteration time τ = 0, within each iteration time step Δτ, for each key component, if the iteration time τ reaches the failure time T failure , the key component enters the fault state, and the system operation state timing vector is updated at this time, and the updated system operation state timing vector and its corresponding fault time T of each key component are determined failure and repair time T repair As input data of τ+Δτ; If the iterative operation time τ reaches the repair time T repair , the key components are restored to the working state, and the system operation state timing vector is updated at this time, and the updated system operation state timing vector and its corresponding failure time T of each key component are determined failure and repair time T repair As input data of τ+Δτ; 3) Within each iterative operation time step Δτ, determine whether a load loss event occurs; Determine whether a load loss event occurs within the iterative calculation time step Δτ. If a load loss event occurs, record the load loss amount caused by the load loss event and the duration of the load loss event. 4) Using the recorded load loss amount and load loss duration, calculate the load loss probability and expected power outage of the integrated energy system; including: The probability of load loss satisfies the following relationship: Where LOLP is the load loss probability of the integrated energy system, T LO is the cumulative value of the duration of each load loss in the comprehensive energy system during the iterative calculation process, T total is the total duration of the iterative operation; The expected unpowered power supply satisfies the following relationship: Where EENS is the expected unpowered energy of the integrated energy system, N LO is the total number of load loss events in the integrated energy system during the iterative calculation process, L ch,i is the load loss caused by the i-th load loss event, t LO,i is the duration of the i-th load loss event.

9. The method for evaluating the operation reliability of an integrated energy system according to claim 1, characterized in that: An operation reliability evaluation model of the integrated energy system is established based on the least squares support vector machine classifier.

10. A comprehensive energy system operation reliability assessment system, characterized in that: include: Key component selection module, used to establish the sensitivity factor index of each electrical node in the integrated energy system to electricity price in each time period; The key nodes in the integrated energy system are determined by using the sensitive factor index of each electrical node to the electricity price in each time period, and the key components are determined from the key nodes by using the operating parameters of each electrical node; The time-varying failure rate calculation module is used to obtain the power response curve of the key components after the implementation of the peak-valley time-of-use electricity price; based on the power response curve of the key components, the load rate of each key component in different time periods is determined, and the failure rate of the key components is corrected by using the load rate of each key component in different time periods to obtain the time-varying failure rate; Operation reliability assessment module, used to establish an operation reliability assessment model for the integrated energy system; determine the failure time of key components based on the time-varying failure rate, and determine the repair time of key components based on the repair rate; The operation reliability assessment model takes the different operation states of the integrated energy system, as well as the failure time and repair time of each key component under each operation state as input data, and outputs the operation reliability index.

Images