A User-Side Energy Storage Method for Improving the Flexibility of the Power Grid

Abstract

The present invention discloses a user-side energy storage method for enhancing the flexibility of the power grid, which relates to the technical fields of smart grid and energy storage. The method includes collecting the electricity load data and electricity price data of user-side power equipment, establishing a load prediction model based on the electricity load data to obtain the predicted value of the electricity load; calculating the charge and discharge time window of the energy storage system based on the electricity price data and the predicted value of the electricity load; generating an optimized scheduling instruction for the energy storage system according to the charge and discharge time window in combination with the capacity constraint of the energy storage system; and controlling the energy storage system to perform charge and discharge operations according to the optimized scheduling instruction. Through intelligent prediction and precise scheduling, the energy storage system can discharge to cut peaks during peak load periods and charge to fill valleys during low load periods, effectively suppressing load fluctuations and enhancing the peak shaving capacity of the power grid. Through real-time monitoring and dynamic adjustment in cooperation with the ramp rate and SOC constraint, the energy storage system can quickly respond to power grid fluctuations and provide flexible power support.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grid and energy storage, and particularly to a user-side energy storage method for improving the flexibility of the power grid. Background Art

[0002] With the rapid progress of renewable energy technologies, the power system is facing an increasingly strong demand for flexibility. The user-side energy storage technology has emerged, effectively regulating the power supply and demand by deploying energy storage devices at the user end. Currently, the power grid not only has to cope with the increasingly fluctuating power demand but also needs to adapt to the intermittent power generation characteristics of renewable energy sources such as wind and solar energy. The driving force behind this transformation comes from the dual pursuit of power system reliability and economy. As a key means to improve the flexibility of the power grid, energy storage technology has received extensive attention. In recent years, the development of user-side energy storage technology has also been accelerating, but there are still many challenges in its implementation process.

[0003] There are several significant deficiencies in the existing user-side energy storage technologies. First of all, the load prediction models often rely too much on historical electricity consumption data and fail to fully consider the changes in user electricity consumption habits, climatic factors, and seasonal fluctuations. This single data dependence makes the prediction results vulnerable to external environmental changes, resulting in insufficient prediction accuracy and affecting the scheduling efficiency of the energy storage system. According to research, the mean absolute percentage error (MAPE) of some load prediction models is above 15%, significantly reducing the economy and benefits of the energy storage system. Secondly, in the existing technologies during the charge and discharge scheduling process, there is a lack of real-time response to electricity price fluctuations. Although some systems can monitor the changes in electricity prices, the scheduling decisions are often lagged, failing to achieve timely charging during low electricity price periods and effective discharging during high electricity price periods. This results in users being unable to fully utilize the electricity price difference to maximize their benefits and reduces the economic efficiency. Finally, the scheduling instructions of many energy storage systems do not reasonably consider the capacity limitations of the energy storage devices, leading to overloading or energy loss. For example, some systems cannot formulate reasonable charge and discharge strategies according to the actual carrying capacity of the power grid and the energy storage capacity during peak load periods, easily resulting in equipment failures or reduced efficiency. Summary of the Invention

[0004] In view of the problems existing in the prior art, the present invention proposes a user-side energy storage method for improving the flexibility of the power grid.

[0005] Therefore, the present invention can solve the problems mentioned in the background art.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a user-side energy storage method for improving the flexibility of the power grid, which includes,

[0008] Collect the electricity consumption load data and electricity price data of the user-side power equipment, establish a load prediction model based on the electricity consumption load data, and obtain the electricity consumption load prediction value;

[0009] Based on the electricity price data and the electricity consumption load prediction value, calculate the charge and discharge time window of the energy storage system:

[0010] According to the charge and discharge time window, combined with the capacity constraint of the energy storage system, generate an optimized scheduling instruction for the energy storage system;

[0011] Send the optimized scheduling instruction to the power converter of the energy storage system, and control the energy storage system to perform charge and discharge operations according to the optimized scheduling instruction.

[0012] As a preferred solution of the user-side energy storage method for improving the flexibility of the power grid according to the present invention, wherein: the electricity consumption load data includes the active power, reactive power, power factor, voltage, and current values at each time period;

[0013] The electricity price data includes peak-valley time-of-use electricity prices, peak electricity prices, and valley electricity prices;

[0014] Construct an enhanced feature vector based on the electricity consumption load data; the enhanced feature vector includes the product term of the load sequence and the time weight, the electricity consumption feature matrix, and the volatility index.

[0015] As a preferred solution of the user-side energy storage method for improving the flexibility of the power grid according to the present invention, wherein: the load prediction model includes a first calculation branch, a second calculation branch, a memory unit, and a residual connection term;

[0016] The first calculation branch receives the input of the enhanced feature vector and outputs in combination with the memory unit, and obtains a first hidden state through processing by a non-linear activation function;

[0017] The second calculation branch receives the input of the enhanced feature vector and combines with the residual connection term, and obtains a second hidden state through processing by a non-linear activation function;

[0018] Use a fusion function to merge the first hidden state and the second hidden state, and correct the prediction result according to the dynamically adjusted adaptive correction coefficient to obtain the electricity consumption load prediction value.

[0019] As a preferred solution of the user-side energy storage method for improving the flexibility of the power grid according to the present invention, wherein: the load prediction model further includes optimizing the load prediction model by using a loss function with a smoothing constraint;

[0020] The smoothing constraint is obtained by calculating the difference between adjacent time prediction values and applying a time decay weight, as shown in the following formula:

[0021] S(t) = ∑|ΔY(t)|·exp(-δt)

[0022] The loss function is as follows:

[0023]

[0024] where is the actual load value at time t, Y(t) is the predicted load value at time t, S(t) is the smoothing constraint term, λ is the weight coefficient, δ is the time decay factor, L * (t) is the loss function, and ΔY(t) is the difference between adjacent times of the predicted value.

[0025] As a preferred solution of the user-side energy storage method for improving the flexibility of the power grid according to the present invention, wherein: the calculation of the charge and discharge time window includes:

[0026] Dividing 24 hours into N time segments by the sliding segmentation method;

[0027] Based on the daily average electricity price P avg Calculate the peak and valley determination thresholds;

[0028] Calculate the load rate Load rate (t), where the load rate is the ratio of the predicted value of the electricity load to the historical maximum load;

[0029] Among them, the charging time corresponds to the electricity price valley period, and the discharging time corresponds to the electricity price peak period;

[0030] During the electricity price valley period, when the electricity price is lower than the valley threshold and the load rate is lower than the first preset value, select 3 or more consecutive time segments to form a charging time window, and the charging window determination condition is expressed as w charge (t) = 1;

[0031] During the electricity price peak period, when the electricity price is higher than the peak threshold and the load rate is higher than the second preset value, select 2 or more consecutive time segments to form a discharging time window, and the discharging window determination condition is expressed as W discharge (t) = 1.

[0032] As a preferred solution of the user-side energy storage method for improving the flexibility of the power grid according to the present invention, wherein: generating an optimized scheduling instruction for the energy storage system includes:

[0033] According to the obtained charge and discharge time window identifiers W charge (t) and W discharge (t), divide a day into multiple charging intervals and discharging intervals;

[0034] Calculate the target charge-discharge power of the time segment t in the charging interval and the discharging interval respectively, and set constraints.

[0035] Calculate the charge-discharge duration of the time segment t in the charging interval and the discharging interval respectively.

[0036] Combine the calculated charge-discharge power sequences and corresponding durations of each time segment to form a scheduling instruction set.

[0037] Each optimized scheduling instruction in the scheduling instruction set includes start and end times, power values, and operating durations.

[0038] As a preferred solution of the user-side energy storage method for improving the flexibility of the power grid according to the present invention, wherein: calculating the target charging power of the time segment t in the charging interval and the discharging interval respectively includes:

[0039] When W charge (t) = 1:

[0040] The calculation of the target charging power is shown in the following formula:

[0041]

[0042] Wherein, P c (t) is the target charging power, P c，max is the maximum charging power, SOC max is the maximum state of charge allowed by the energy storage system, SOC(t - 1) is the state of charge of the time segment t - 1, E rated is the rated capacity, η c is the charging efficiency, and Δt is the length of each time segment;

[0043] When W discharge (t) = 1:

[0044] The calculation of the target discharging power is shown in the following formula:

[0045]

[0046] Wherein, P c (t) is the target discharging power, P d，max is the maximum discharging power, η d is the discharging efficiency, and SOC min is the minimum state of charge allowed by the energy storage system.

[0047] As a preferred solution of the user-side energy storage method for improving the flexibility of the power grid according to the present invention, wherein: the charge-discharge duration includes:

[0048] The charging duration is calculated according to the target SOC increment and the integral of the charging power of each time segment in the charging interval, as shown in the following formula:

[0049] T c = ∑(Δt·W charge (t))

[0050] The discharge duration is calculated by integrating the target SOC reduction and discharge power of each time segment within the discharge interval, as shown in the following formula:

[0051] T d = ∑(Δt·W discharge (t))

[0052] Wherein, T c is the charging duration, and T d is the discharge duration.

[0053] In a second aspect, an embodiment of the present invention provides a user-side energy storage system for improving the flexibility of the power grid, which includes:

[0054] A data acquisition module for collecting the power consumption load data and electricity price data of user-side power equipment;

[0055] A power consumption load prediction module for establishing a load prediction model based on the power consumption load data to obtain a power consumption load prediction value;

[0056] A charge and discharge time window calculation module for calculating the charge and discharge time window of the energy storage system based on the electricity price data and the power consumption load prediction value;

[0057] A scheduling instruction generation module for generating an optimized scheduling instruction for the energy storage system according to the charge and discharge time window and in combination with the capacity constraint of the energy storage system; controlling the energy storage system to perform charge and discharge operations according to the optimized scheduling instruction.

[0058] The beneficial effects of the present invention are as follows: by using high-precision acquisition equipment to obtain power consumption load and electricity price data, then using a prediction model constructed by a dual-stream neural network to accurately predict the power consumption load, determining the optimal charge and discharge time window based on the prediction result and the time-of-use electricity price, and finally generating detailed scheduling instructions according to the various constraints of the energy storage system, so as to achieve the economic scheduling goal of storing energy during the low electricity price period and discharging during the high electricity price period, effectively reducing the electricity cost while improving the stability of the power grid operation. Through intelligent prediction and precise scheduling, the energy storage system can discharge during peak load periods to shave peaks and charge during low load periods to fill valleys, effectively suppressing load fluctuations and enhancing the peak shaving ability of the power grid; at the same time, the system can quickly respond to power grid fluctuations and provide flexible power support by real-time monitoring of the load rate and power factor and coordinating the dynamic adjustment of the ramp rate and SOC constraint, enhancing the dynamic adjustment ability of the power grid; this active control mode based on prediction significantly improves the operation flexibility of the power grid compared with the traditional passive response method. Description of the Drawings

[0059] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative work, other drawings can be obtained based on these drawings. Among them:

[0060] Figure 1 Flowchart of the user-side energy storage method for enhancing the flexibility of the power grid. Detailed implementation manners

[0061] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific implementation manners of the present invention in conjunction with the drawings of the specification. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0062] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0063] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that mutually excludes other embodiments.

[0064] The present invention is described in detail in conjunction with schematic diagrams. When detailing the embodiments of the present invention, for the convenience of explanation, the cross-sectional views showing the device structure will be enlarged locally out of the general proportion, and the schematic diagrams are only examples, which should not limit the protection scope of the present invention herein. In addition, in actual production, three-dimensional spatial dimensions including length, width, and depth should be included.

[0065] At the same time, in the description of the present invention, it should be noted that the orientation or positional relationship indicated by terms such as "upper, lower, inner, and outer" is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation to the present invention. In addition, the terms "first, second, or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0066] Unless otherwise clearly specified and defined in the present invention, the terms "installation, connection, and coupling" shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may also be a mechanical connection, an electrical connection, or a direct connection, and may also be indirectly connected through an intermediate medium, or may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0067] Embodiment 1

[0068] Referring to Figure 1 , which is the first embodiment of the present invention. This embodiment provides a user-side energy storage method for improving the flexibility of the power grid, including:

[0069] S1: Collect the power consumption load data and electricity price data of the user-side power equipment, and transmit the power consumption load data and the electricity price data to the control unit through a data collection device;

[0070] Collect the power consumption load data of the user-side power equipment, where the power consumption load data includes: active power, reactive power, power factor, voltage, and current values at each time period; collect the electricity price data of the power grid operation, and the electricity price data includes: time-of-use electricity price, peak electricity price, and valley electricity price; the data collection device is provided with an electric energy metering module and a communication module, and the power consumption load data of the user side is recorded in real time through the electric energy metering module, and the sampling period is 15 minutes; the communication module uses the RS485 communication method to establish a connection with the power grid dispatching system to obtain the electricity price data; transmit the power consumption load data and the electricity price data to the data processing module of the control unit through the communication module, and the data processing module performs standardization processing and data quality verification on the received data.

[0071] S2: Establish a load prediction model according to the power consumption load data;

[0072] Establish a load prediction model according to the power consumption load data. The specific construction process of the load prediction model includes: dividing the power consumption load data into a training data set and a verification data set according to time series, where the training data set accounts for 80%, and the verification data set accounts for 20%; constructing an enhanced feature vector through multiple feature extractions based on the power consumption load data. The enhanced feature vector includes three components: the product term of the load sequence and the time weight, the power consumption feature matrix, and the volatility index, and a dynamic adjustment factor is introduced to adaptively adjust the feature vector, and its calculation formula can be expressed by the following formula:

[0073] X(t) = [L(t)·W(t), E(t), V(t)]·θ(t)

[0074] Among them, \(L(t)\) represents the load sequence, \(W(t)\) is the time weight coefficient, \(E(t)\) is the electricity consumption feature matrix, \(V(t)\) is the volatility index, and \(\theta(t)\) is the dynamic adjustment factor.

[0075] The load prediction model adopts a two-stream neural network structure. The first calculation branch receives the input of the enhanced feature vector and outputs in combination with the memory unit. The second calculation branch also receives the input of the enhanced feature vector and introduces a residual connection term. The outputs of the two branches are processed by a non-linear activation function to form two hidden states respectively. Its core calculation process can be expressed by the following formula:

[0076] \(H1(t)=\sigma(W1\cdot X(t)+\alpha\cdot M(t))\)

[0077] \(H2(t)=\sigma(W2\cdot X(t)+\beta\cdot R(t))\)

[0078] \(Y(t)=\varphi(H1(t),H2(t))\cdot K(t)\)

[0079] Among them, \(H1(t)\) and \(H2(t)\) are the hidden states of the two parallel branches respectively, \(M(t)\) is the output of the memory unit, \(R(t)\) is the residual connection term, \(K(t)\) is the adaptive correction coefficient, \(\alpha\) and \(\beta\) are balance parameters, \(Y(t)\) is the predicted value of electricity load, \(W1\) and \(W2\) are the weight matrices of the neural network, \(\varphi()\) is a fusion function used to combine the outputs of the two branches, and \(\sigma\) is the activation function;

[0080] Then, the two hidden states are combined through a fusion function, and the prediction result is corrected by an adaptive correction coefficient, where the adaptive correction coefficient is dynamically adjusted according to the prediction error; the optimization of the prediction model uses a loss function with a smoothing constraint, and the smoothing constraint is obtained by calculating the difference between the predicted values at adjacent times and applying a time decay weight, which is used to suppress the sharp fluctuations of the prediction result. Specifically, it is shown in the following formula:

[0081]

[0082] \(S(t)=\sum|\Delta Y(t)|\cdot\exp(-\delta t)\)

[0083] Among them, is the actual load value, \(S(t)\) is the smoothing constraint term, \(\lambda\) is the weight coefficient, \(\delta\) is the time decay factor, \(L^*(t)\) is the loss function, and \(\Delta Y(t)\) is the difference between the predicted values at adjacent times.

[0084] Finally, the load prediction model is trained by the Adam optimization algorithm, and the number of training rounds is set to 200 rounds.

[0085] It should be noted that the acquisition of the L(t) load sequence extracts the historical load values of the most recent 168 hours from the electricity load data to form an initial sequence, and performs normalization processing on the initial sequence, with the normalization interval set to [-1, 1]; the load sequence is updated by means of a sliding time window, and the window length is set to 168 hours;

[0086] The calculation of the W(t) time weight coefficient is based on the time correlation of the load sequence, and an exponential decay function is used to calculate the weight coefficient. The data closer to the prediction time is given a larger weight value, and the weight coefficient takes values in the interval [0.6, 1], and the decay rate is set to 0.05;

[0087] The construction of the E(t) electricity consumption feature matrix includes segmenting the electricity load data in 24-hour periods, and extracting statistical features such as the maximum value, minimum value, mean value, and standard deviation within each segment to form a 4×24-dimensional feature matrix, and the feature matrix is updated every 24 hours;

[0088] The determination of the V(t) volatility index is based on the first-order difference value of the load sequence, calculates the load change rate at adjacent moments, and obtains the volatility index through exponential smoothing method, with the smoothing coefficient set to 0.3, and the volatility index is updated every hour;

[0089] The generation of the θ(t) dynamic adjustment factor is based on the change trend of the load prediction error, and an adaptive algorithm is used to calculate the adjustment factor. When the prediction error increases, the adjustment factor decreases accordingly, and the value range is limited between [0.8, 1.2];

[0090] The acquisition of the output of the M(t) memory unit is obtained by recursively processing the load sequence features. The memory unit adopts a gated structure, including three control units: an input gate, a forget gate, and an output gate, and the threshold values are all set to 0.5;

[0091] The calculation of the R(t) residual connection term performs a difference operation on the input feature and the output of the previous layer network, and performs feature mapping through a 1×1 convolutional kernel to obtain the residual connection term, which is used to retain low-level feature information;

[0092] The update of the K(t) adaptive correction coefficient is based on the statistical distribution of the prediction error, and a normalized exponential function is used to calculate the correction coefficient. When the prediction error exceeds the set threshold, the correction mechanism is triggered, and the value range of the correction coefficient is [0.9, 1.1].

[0093] S3: Based on the electricity price data and the predicted value of the electricity load, calculate the charge and discharge time windows of the energy storage system, where the charging time corresponds to the low electricity price period, and the discharging time corresponds to the high electricity price period;

[0094] Based on the electricity price data and the predicted value of the electricity load, calculate the charge and discharge time windows of the energy storage system. The calculation process includes:

[0095] Divide 24 hours into N time segments by the sliding segmentation method, and the length of each time segment is 30 minutes; based on the daily average electricity price P avg Calculate the peak and valley determination thresholds. The peak threshold P high is 1.2 times the daily average electricity price, and the valley threshold Pl ow is 0.85 times the daily average electricity price; calculate the load factor Load rate (t) of each time segment, and the load factor is the ratio of the predicted load value to the historical maximum load.

[0096] During the valley period, when the electricity price is lower than the valley threshold and the load factor is lower than 0.7, select 3 or more consecutive time segments to form a charging time window, and the charging window determination condition is expressed as W charge (t) = 1.

[0097] During the peak period, when the electricity price is higher than the peak threshold and the load factor is higher than 0.85, select 2 or more consecutive time segments to form a discharging time window, and the discharging window determination condition is expressed as W discharge (t) = 1.

[0098] The time interval Δt between the charging time window and the discharging time window is not less than 2 hours;

[0099] It should be noted that the electricity price data is denoted as P(t), representing the electricity price value at time t; calculate the daily average electricity price P avg :

[0100]

[0101] The calculation process of the charging window identifier W charge (t) is as follows:

[0102] W charge (t) = AND(P flag (t), L flag (t), C flag (t))

[0103] where, when P(t) < P low , P flag (t) = 1;

[0104] When Load rate (t) < 0.7, L flag (t) = 1;

[0105] When the number of time segments continuously meeting the above conditions ≥ 3, C flag (t) = 1;

[0106] The discharge window identifier W discharge (t) is calculated as follows:

[0107]

[0108] Where:

[0109] When P(t) > P high At that time,

[0110] When Load rate (t) > 0.85,

[0111] When the number of time segments continuously meeting the above conditions ≥ 2, D flag (t) = 1;

[0112] Among them, P flag (t) is the low - price valley identifier of electricity price, L flag (t) is the low - load rate identifier, C flag (t) is the charging continuity identifier, is the high - price peak identifier of electricity price, is the high - load rate identifier, D flag (t) is the discharge continuity identifier.

[0113] S4: Based on the charge - discharge time window, combined with the capacity constraint of the energy storage system, generate an optimized scheduling instruction for the energy storage system, and the optimized scheduling instruction includes charge - discharge power and charge - discharge duration;

[0114] First, based on the 48 time segments (each segment is 30 minutes) obtained by sliding segmentation, according to the obtained charge - discharge time window identifiers W charge (t) and W discharge (t), divide a day into multiple charging intervals and discharge intervals. Mark each continuous time segment with W charge (t) = 1 as a charging interval, and mark each continuous time segment with W discharge (t) = 1 as a discharge interval.

[0115] Then set the constraints of the energy storage system, including the rated capacity E rated , the maximum charging power P c，max , the maximum discharge power P d，max and the safe operation interval of the state of charge SOC [SOC min , SOC max , where SOC minSet to 0.1, SOC max Set to 0.9, the charge and discharge efficiencies are η c and η d , and the power ramp rate limit is δP max . Specific constraints include:

[0116] SOC min ≤SOC(t)≤SOC max

[0117] -P d，max ≤P(t)≤P c，max

[0118] |P(t)-P(t - 1)|≤δP max

[0119] It should be noted that the state - of - charge evolution equation is as follows:

[0120]

[0121] where t is the time segment within the charging interval.

[0122] Furthermore, for the time segment t within the charging interval, based on the load rate Load rate (t) and the electricity price P(t), calculate the target charging power P c (t). When the load rate Load rate (t)<0.7 and the electricity price P(t)<P low , select a larger charging power, and the charging power needs to satisfy the maximum power limit, SOC upper - limit constraint, and ramp - rate limit simultaneously. For the charging interval t, when W charge (t) = 1:

[0123] Power calculation:

[0124]

[0125] Load - rate constraint:

[0126] if Load rate (t)<0.7: P c (t) = α·P c，max

[0127] Ramp - rate limit:

[0128] |P c (t)-P c (t - 1)|≤δP max

[0129] Furthermore, for the time segment t within the discharging interval, based on the load rate Loadrate (t) and electricity price P(t) are used to calculate the target discharge power P d (t). When the load factor Load rate (t)>0.85 and the electricity price P(t) > P high , a larger discharge power is selected. The discharge power needs to satisfy the maximum power limit, SOC lower limit constraint, and ramp rate limit at the same time. For the discharge interval t, when W discharge (t) = 1:

[0130] Power calculation:

[0131]

[0132] Load factor constraint:

[0133] if Load rate (t)>0.85: P d (t) = β·P d，max

[0134] Ramp constraint:

[0135] |P d (t)-P d (t - 1)| ≤ δP max

[0136] Furthermore, the charging duration and discharge duration are calculated. The charging duration T c is calculated according to the target SOC increment and charging power integral of each time segment within the charging interval. The discharge duration T d is calculated according to the target SOC decrement and discharge power integral of each time segment within the discharge interval, and the charge and discharge intervals need to meet the minimum continuous time segment number requirement. Specific calculation:

[0137] T c = ∑(Δt·W charge (t))

[0138] T d = ∑(Δt·W discharge (t))

[0139] Its charge and discharge energy balance constraint:

[0140]

[0141] Finally, the charge and discharge power sequences and corresponding durations of each time segment calculated are combined to form a scheduling instruction set. Each instruction contains the start and end times, power value, and running duration. The interval between adjacent charge and discharge intervals is not less than 4 time segments (i.e., 2 hours). Ramp transition instructions are generated for the power change points, and appropriate power adjustment margins are reserved.

[0142] Send the optimized scheduling instruction to the power converter of the energy storage system, and control the energy storage system to perform charge and discharge operations according to the optimized scheduling instruction.

[0143] Furthermore, this embodiment also provides a user-side energy storage system for enhancing grid flexibility, including:

[0144] A data acquisition module for acquiring the power consumption load data and electricity price data of user-side power equipment;

[0145] A power consumption load prediction module for establishing a load prediction model based on the power consumption load data to obtain a power consumption load prediction value;

[0146] A charge and discharge time window calculation module for calculating the charge and discharge time window of the energy storage system based on the electricity price data and the power consumption load prediction value;

[0147] A scheduling instruction generation module for generating an optimized scheduling instruction for the energy storage system based on the charge and discharge time window and in combination with the capacity constraint of the energy storage system; controlling the energy storage system to perform charge and discharge operations according to the optimized scheduling instruction.

[0148] This embodiment also provides a computer device applicable to the case of the user-side energy storage method for enhancing grid flexibility, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the user-side energy storage method for enhancing grid flexibility as proposed in the above embodiment.

[0149] This computer device can be a terminal, and this computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of this computer device is used to provide computing and control capabilities. The memory of this computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of this computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of this computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of this computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0150] This embodiment also provides a storage medium, on which a computer program is stored, and when this program is executed by a processor, it implements the user-side energy storage method for realizing enhanced grid flexibility as proposed in the above embodiment.

[0151] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. Technical details not described in detail in this embodiment can be referred to in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0152] Embodiment 2

[0153] This is the second embodiment of the present invention. This embodiment provides a user-side energy storage method for improving the flexibility of the power grid. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0154] This test was carried out in an industrial park, and a 10MW / 40MWh lithium-ion battery energy storage power station in the park was selected as the test object. Before the test, a comprehensive inspection of the energy storage system was carried out to ensure that all performance parameters meet the requirements. The data acquisition system uses Schneider PM5560 high-precision watt-hour meters and ABB RTU 560 data acquisition terminals to transmit data to the data processing server in the central control room through the RS485 bus. The sampling period is set to 15 minutes, and 30 days of historical operation data are continuously collected as the basis for model training.

[0155] To verify the optimization scheduling effect of the present invention, the park is divided into two areas, Area A and Area B, for a comparative test. Area A adopts the traditional fixed-time scheduling strategy, and Area B adopts the intelligent optimization scheduling scheme of the present invention. During the test, the power consumption load data of the two areas are recorded in real time through the data acquisition device, including active power, reactive power, power factor, voltage and current values at 15-minute intervals. At the same time, real-time electricity price data are obtained from the power grid dispatching system, including peak-valley time-of-use electricity prices, peak electricity prices and valley electricity prices.

[0156] The data processing module performs standardization processing and quality verification on the collected data, and inputs the data into the load prediction model after removing outliers. The prediction model adopts the dual-stream neural network structure proposed in the present invention. Based on 168 hours of historical data, an enhanced feature vector is constructed by combining time weights, electricity consumption feature matrices and volatility indicators. The model training adopts the Adam optimization algorithm, with a learning rate set to 0.001 and 200 training rounds. The prediction results are compared with the actual load to verify the prediction accuracy.

[0157] Based on the predicted load and electricity price data, the system automatically calculates the charge and discharge time windows of the energy storage system. Through a sliding segmentation in units of 30 minutes, combined with the peak threshold of 1.2 times the average daily electricity price and the valley threshold of 0.85 times the average daily electricity price, the optimal charge and discharge intervals are determined. Under the conditions of meeting the SOC constraint [0.1, 0.9], the power ramp rate limit of ±20% of the rated power per minute, etc., detailed charge and discharge scheduling instructions are generated. The specific experimental data are shown in Table 1 below:

[0158] Table 1 Experimental data table

[0159]

[0160]

[0161] Through the analysis of the comparative test data, it can be seen that the optimized scheduling scheme (Zone B) of the present invention has significant advantages compared with the traditional fixed-time scheduling strategy (Zone A):

[0162] The average load rate in Zone B is increased to 82.3%, which is 4.8 percentage points higher than that in Zone A, indicating that the optimized scheduling scheme can better suppress load fluctuations. The peak-valley difference increases from 4.2 MW to 6.8 MW, an increase of 61.9%, indicating that the system has stronger peak-shaving ability.

[0163] The price-sensitive response time is reduced from 25 minutes to 12 minutes, an increase of 52%, reflecting the advantage of the present invention in terms of market response speed. This benefits from the synergistic effect of the prediction model of the dual-stream neural network structure and the dynamic adjustment mechanism.

[0164] The daily income under the optimized scheduling scheme reaches 4,260 yuan, a 49.5% increase compared with the traditional scheme. The charge-discharge cycle efficiency is increased by 4.1 percentage points to reach 88.7%, which is mainly due to the more accurate selection of the charge-discharge time window and power optimization control.

[0165] The power factor in Zone B is increased to 0.95, and the power quality improvement rate reaches 15.3%, which is 3.3% and 80% higher than that in Zone A respectively. This indicates that the present invention not only optimizes the economic benefits but also can effectively improve the power quality index.

[0166] To verify the stability and reliability of the scheme, parallel tests were carried out in four regions C, D, E, and F. The data shows that the fluctuation range of the performance indicators in each region is small: the average load rate is between 81.9% and 83.1%, the response time is between 11 and 13 minutes, the daily income is between 4,180 and 4,380 yuan, and the charge-discharge efficiency is between 88.5% and 89.1%. This stable performance confirms that the scheme of the present invention has good adaptability and generalizability.

[0167] In summary, the energy storage optimized scheduling scheme proposed by the present invention is significantly superior to the traditional scheme in terms of load regulation ability, market response speed, economic benefits, and power quality, and has good stability and reliability. This scheduling strategy based on intelligent prediction and multi-constraint optimization provides a new technical path for the efficient utilization of energy storage systems.

[0168] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A user-side energy storage method for improving the flexibility of the power grid, characterized in that: Including: Collecting the electricity load data and electricity price data of the user-side power equipment, establishing a load forecasting model based on the electricity load data, and obtaining the electricity load forecasting value; Calculating the charge and discharge time window of the energy storage system based on the electricity price data and the electricity load forecasting value; Generating an optimized scheduling instruction for the energy storage system according to the charge and discharge time window, in combination with the capacity constraint of the energy storage system; Sending the optimized scheduling instruction to the power converter of the energy storage system to control the energy storage system to perform charge and discharge operations according to the optimized scheduling instruction; The electricity load data includes the active power, reactive power, power factor, voltage, and current values in each time period; The electricity price data includes peak-valley time-of-use electricity price, peak electricity price, and valley electricity price; Constructing an enhanced feature vector based on the electricity load data; the enhanced feature vector includes the product term of the load sequence and the time weight, the electricity consumption feature matrix, and the volatility index; The load forecasting model includes a first calculation branch, a second calculation branch, a memory unit, and a residual connection term; The first calculation branch receives the input of the enhanced feature vector and outputs in combination with the memory unit, and obtains a first hidden state through processing by a non-linear activation function; The second calculation branch receives the input of the enhanced feature vector and combines it with the residual connection term, and obtains a second hidden state through processing by a non-linear activation function; Using a fusion function to merge the first hidden state and the second hidden state, and correcting the prediction result according to the adaptively adjusted adaptive correction coefficient to obtain the electricity load forecasting value; The load forecasting model also includes optimizing the load forecasting model by using a loss function with a smoothing constraint; The smoothing constraint is obtained by calculating the difference between the predicted values at adjacent times and applying a time decay weight, as shown in the following formula: ； The loss function is as shown in the following formula: ； wherein, is the actual load value at the moment, is the predicted load value at the moment, is the smoothing constraint term, is the weight coefficient, is the time decay factor, is the loss function, is the difference between adjacent moments of the predicted value; Generating an optimized scheduling instruction for the energy storage system includes: According to the obtained charge and discharge time window identifiers and , a day is divided into multiple charging intervals and discharging intervals; Calculating the target charge and discharge power of the time segments in the charge interval and the discharge interval respectively, and setting constraints; Calculate the time segments of the charging interval and the discharging interval respectively for the charging and discharging durations; Combining the calculated charge and discharge power sequences and corresponding durations of each time segment to form a scheduling instruction set; Each optimized scheduling instruction in the scheduling instruction set includes the start and end times, power value, and running duration.

2. The user-side energy storage method for improving the flexibility of the power grid according to claim 1, characterized in that: The calculation of the charge and discharge time window includes: Dividing 24 hours into N time segments by a sliding segmentation method; Based on the daily average electricity price Calculate the peak and trough determination thresholds; Calculate the load rate for each time segment , where the load rate is the ratio of the predicted value of the electricity load to the historical maximum load; Among them, the charging time corresponds to the electricity price valley period, and the discharging time corresponds to the electricity price peak period; During the low electricity price period, when the electricity price is lower than the low threshold and the load factor is lower than the first preset value, select three or more consecutive time segments to form a charging time window, and the charging window determination condition is expressed as = 1; During the peak electricity price period, when the electricity price is higher than the peak threshold and the load factor is higher than the second preset value, select two or more consecutive time segments to form a discharge time window, and the discharge window determination condition is expressed as = 1 3. The user-side energy storage method for enhancing the flexibility of the power grid according to claim 2, wherein: Calculate the time segments of the charging interval and the discharging interval respectively The target charging power of When = 1: The calculation of the target charging power is as shown in the following formula: ； Among them, is the target charging power, is the maximum charging power, is the maximum state of charge allowed by the energy storage system, is the time segment of the state of charge, is the rated capacity, is the charging efficiency, is the length of each time segment; When = 1: The calculation of the target discharging power is as shown in the following formula: ； Among them, is the target discharge power, is the maximum discharge power, is the discharge efficiency, is the minimum state of charge allowed by the energy storage system.

4. The user-side energy storage method for improving the flexibility of the power grid according to claim 3, characterized in that: The charge and discharge duration includes: The charging duration is calculated according to the target SOC increment and the integral of the charging power in each time segment within the charging interval, as shown in the following formula: ； The discharging duration is calculated according to the target SOC decrement and the integral of the discharging power in each time segment within the discharging interval, as shown in the following formula: ； Among them, is the charging duration, is the discharging duration.

5. A user-side energy storage system for enhancing the flexibility of the power grid, based on the user-side energy storage method for enhancing the flexibility of the power grid according to any one of claims 1 to 4, characterized in that: Including: A data acquisition module for collecting the electricity load data and electricity price data of the user-side power equipment; An electricity load forecasting module for establishing a load forecasting model based on the electricity load data and obtaining the electricity load forecasting value; A charge-discharge time window calculation module, which is used to calculate the charge-discharge time window of the energy storage system based on the electricity price data and the predicted value of the electricity load; A scheduling instruction generation module, which is used to generate an optimized scheduling instruction for the energy storage system according to the charge-discharge time window and in combination with the capacity constraint of the energy storage system; and control the energy storage system to perform charge-discharge operations according to the optimized scheduling instruction.

Images