Power grid resource optimization method and device based on multi-dimensional entropy theory, equipment and medium

Abstract

The invention discloses a multi-dimensional entropy theory-based power grid resource optimization method, device, equipment and medium, and the method comprises the steps: calculating a load fluctuation rate, a resource utilization rate and an electric energy loss rate of a power distribution node based on real-time operation data and historical load data of the power distribution node; the method comprises the following steps: respectively calculating an entropy value of a load fluctuation rate, an entropy value of a resource utilization rate and an entropy value of an electric energy loss rate, carrying out weighted summation on the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate and the entropy value of the electric energy loss rate to obtain a multi-dimensional entropy, predicting a load of a power distribution node based on historical load data, generating a load trend prediction function, and carrying out prediction. Based on the real-time operation data, the load trend prediction function and the multi-dimensional entropy, the resource distribution proportion of the power distribution nodes is adaptively regulated and controlled, the uncertainty of the power grid system is quantitatively analyzed based on the multi-dimensional entropy theory, the resource distribution proportion of the power distribution nodes is adaptively regulated and controlled, and dynamic load balance and optimal resource configuration of the power distribution nodes are achieved.

Description

Technical Field

[0001] The present invention relates to power grid resource optimization technology, and in particular to a power grid resource optimization method, device, equipment and medium based on multidimensional entropy theory. Background Art

[0002] With the continuous growth of electricity demand and the expansion of the scale of new energy access, the distribution network faces more and more challenges in its operation. The power system needs to reasonably allocate resources among the distribution nodes to meet the load demands of different regions and times. Due to the volatility and uncertainty of load, the traditional distribution system faces many limitations in resource allocation and regulation, making it difficult to achieve dynamic balance and efficient management.

[0003] At present, the resource allocation of most distribution networks relies on fixed dispatching strategies or manual intervention. Fixed dispatching strategies set static load distribution rules based on historical experience. When the actual load fluctuates greatly, it is often difficult to respond in time, resulting in overload of some nodes, unbalanced resource allocation, and even power outages. The manual intervention mode is not only inefficient but also unable to adapt to complex load changes in real time, increasing the cost of power grid operation and maintenance.

[0004] Some modern distribution systems have tried to use simple automated control technologies, such as prediction algorithms based on time series analysis to optimize scheduling. These technologies can usually only handle load changes in a single dimension and fail to fully consider the uncertainty and complexity in the system. In a complex distribution network environment, uncertain factors such as fluctuations in renewable energy generation, random changes in user loads, and line failures pose a huge challenge to the smooth operation of the power grid. Existing automated control technologies often find it difficult to cope with these uncertain factors, resulting in inefficient resource utilization, large energy losses, and the possibility that local nodes are overloaded while other node resources are idle.

[0005] In summary, the existing distribution network has significant deficiencies in load fluctuation management, resource utilization efficiency, and control response speed. Traditional fixed scheduling strategies and simple prediction algorithms cannot fully cope with the uncertainty challenges in complex power grids, and it is difficult to achieve efficient resource allocation and smooth node operation. These problems lead to waste of power resources, increased overload risks, and reduced overall power grid operation efficiency. Therefore, there is an urgent need for a control method based on more advanced intelligent algorithms to effectively deal with uncertainties in the power grid and achieve dynamic load balancing and optimal resource configuration for each distribution node. Summary of the invention

[0006] The present invention provides a power grid resource optimization method, device, equipment and medium based on multi-dimensional entropy theory to achieve dynamic load balancing and optimal resource configuration of each distribution node.

[0007] In a first aspect, the present invention provides a method for optimizing power grid resources based on multidimensional entropy theory, comprising:

[0008] Obtain real-time operation data and historical load data of each distribution node in the distribution network;

[0009] Calculate the load fluctuation rate, resource utilization rate and power loss rate of the power distribution node based on the real-time operation data and the historical load data of the power distribution node;

[0010] respectively calculating the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate, and the entropy value of the power loss rate;

[0011] Taking a weighted sum of the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate, and the entropy value of the power loss rate to obtain a multidimensional entropy;

[0012] Predicting the load of the power distribution node based on the historical load data, and generating a load trend prediction function;

[0013] The resource allocation ratio of the power distribution node is adaptively regulated based on the real-time operation data, the load trend prediction function and the multi-dimensional entropy.

[0014] Optionally, the calculation formula for the load fluctuation rate of the power distribution node is:

[0015]

[0016] Among them, F var-combined (t,T) is the load fluctuation rate of the distribution node, P(t i ) is t i The real-time load value at the moment, P(T j ) is the time period T j The historical load value within To combine the load average of real-time and historical data, n and m are the total number of real-time data points and historical data points, respectively;

[0017] The calculation formula of the resource utilization is:

[0018]

[0019] Among them, η combined (t,T) is the resource utilization of the distribution node, P out (t) and P in (t) respectively represent the output power and input power in the real-time operation data, P out (T) and P in (T) represents the output power and input power in the historical load data respectively;

[0020] The calculation formula of the power loss rate is:

[0021]

[0022] Among them, L loss-combined (t,T) is the power loss rate of the distribution node.

[0023] Optionally, the calculation formula of the entropy value of the load fluctuation rate is:

[0024] H1=-∑F var-combined (t,T)log(F var-combined (t,T)

[0025] Among them, H1 is the entropy value of load fluctuation rate, F var-combined (t,T) is the load fluctuation rate of the distribution node;

[0026] The calculation formula of the entropy value of the resource utilization is:

[0027] H2=-∑η combined (t,T)log(η combined (t,T)

[0028] Among them, H2 is the entropy value of resource utilization, η combined (t,T) is the resource utilization of the distribution node;

[0029] The calculation formula of the entropy value of the power loss rate is:

[0030] H3=-∑L loss-combined (t,T)log(L loss-combined (t,T)

[0031] Among them, H3 is the entropy value of the power loss rate, L loss-combined (t,T) is the power loss rate of the distribution node.

[0032] Optionally, predicting the load of the distribution node based on the historical load data to generate a load trend prediction function includes:

[0033] Decomposing the historical load data at multiple time scales to obtain historical load data at multiple time scales;

[0034] Extracting trend items and fluctuation items of the historical load data at different time scales;

[0035] Based on the trend items and fluctuation items of the historical load data at different time scales, predict the predicted values ​​of the trend items and fluctuation items of the historical load data at different time scales at future moments;

[0036] Calculating multidimensional entropy of the historical load data at different time scales;

[0037] A load trend prediction function is generated based on the multidimensional entropy of the historical load data at different time scales and the predicted values ​​of the trend item and the fluctuation item of the historical load data at different time scales at future moments.

[0038] Optionally, the expression of the load trend prediction function is:

[0039]

[0040] Among them, C load-predict (t+Δt) is the predicted value of the load, S is the Sth time scale, E s is the multidimensional entropy of the historical load data at the Sth time scale, is the predicted value of the trend item at the future moment, is the predicted value of the volatility term at future moments.

[0041] Optionally, the mathematical expression for adaptively regulating the resource allocation ratio of the power distribution node based on the real-time operation data, the load trend prediction function and the multi-dimensional entropy is:

[0042]

[0043] Among them, M adaptive (t) is the resource allocation ratio at time t, α i , β i and γ i is the adaptive coefficient, E entropy (t) is the multidimensional entropy, D real-time (t) is the real-time operation data, C load-predict (t+Δt) is the predicted value of the load.

[0044] Optionally, the power grid resource optimization method based on multidimensional entropy theory also includes:

[0045] Determining whether the predicted value of the load reaches a load peak threshold;

[0046] If so, perform resource scheduling and regulation in advance.

[0047] In a second aspect, the present invention further provides a power grid resource optimization device based on multidimensional entropy theory, comprising:

[0048] A data acquisition module is used to obtain real-time operation data and historical load data of each distribution node in the distribution network;

[0049] An uncertainty index calculation module, used to calculate the load fluctuation rate, resource utilization rate and power loss rate of the distribution node based on the real-time operation data and the historical load data of the distribution node;

[0050] An entropy value calculation module, used to respectively calculate the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate and the entropy value of the power loss rate;

[0051] A weighted summation module, used for weighted summation of the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate and the entropy value of the power loss rate to obtain a multi-dimensional entropy;

[0052] A load prediction function generating module, used to predict the load of the distribution node based on the historical load data and generate a load trend prediction function;

[0053] A resource allocation control module adaptively controls the resource allocation ratio of the distribution node based on the real-time operation data, the load trend prediction function and the multi-dimensional entropy.

[0054] In a third aspect, the present invention further provides an electronic device, comprising:

[0055] one or more processors;

[0056] A storage device for storing one or more programs;

[0057] When the one or more programs are executed by the one or more processors, the one or more processors implement the power grid resource optimization method based on multi-dimensional entropy theory as provided in the first aspect of the present invention.

[0058] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the power grid resource optimization method based on multidimensional entropy theory as provided in the first aspect of the present invention.

[0059] The power grid resource optimization method based on multidimensional entropy theory provided by the present invention obtains real-time operation data and historical load data of each distribution node in the distribution network, calculates the load fluctuation rate, resource utilization rate and electric energy loss rate of the distribution node based on the real-time operation data and historical load data of the distribution node, calculates the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate and the entropy value of the electric energy loss rate respectively, performs weighted summation on the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate and the entropy value of the electric energy loss rate to obtain multidimensional entropy, predicts the load of the distribution node based on the historical load data, generates a load trend prediction function, adaptively adjusts the resource allocation ratio of the distribution node based on the real-time operation data, the load trend prediction function and the multidimensional entropy, quantitatively analyzes the uncertainty of the power grid system based on the multidimensional entropy theory, and adaptively adjusts the resource allocation ratio of the distribution node to achieve dynamic load balancing and optimal resource configuration of each distribution node.

[0060] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0062] Figure 1 A flowchart of a power grid resource optimization method based on multidimensional entropy theory provided by the present invention;

[0063] Figure 2 A schematic diagram of the structure of a power grid resource optimization device based on multi-dimensional entropy theory provided by the present invention;

[0064] Figure 3 The present invention provides a schematic structural diagram of an electronic device.

[0065] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0066] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0067] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0068] Figure 1 This is a flow chart of a method for optimizing power grid resources based on multidimensional entropy theory provided by the present invention. This embodiment can perform real-time regulation of the resources of distribution nodes based on multidimensional entropy theory. This method can be performed by a power grid resource optimization device based on multidimensional entropy theory provided by an embodiment of the present invention. The device can be implemented by software and / or hardware, and is usually configured in an electronic device, such as Figure 1 As shown, the power grid resource optimization method based on multidimensional entropy theory includes the following steps:

[0069] S101. Acquire real-time operation data and historical load data of each distribution node in the distribution network.

[0070] In the embodiment of the present invention, each distribution node in the distribution network is monitored by a sensor network, real-time operation data of the distribution node is obtained, and a real-time operation data set D of each distribution node is constructed. real-time :

[0071] D real-time (t)={P(t),W(t),V(t),I(t),L(t)}

[0072] Among them, P(t), W(t), V(t), I(t), and L(t) respectively represent the real-time values ​​of the load, power consumption, distribution node voltage, distribution node current, and line loss of the distribution node at time t.

[0073] Collect the load change data of each distribution node in different time periods and build a historical load data set D historical , where the historical load data of each node is expressed as:

[0074] D historical = {P(t i )|t i ∈[t0,t n ]};

[0075] Among them, P(ti ) represents the distribution node at time t i The load value at the time, the time interval [t0,t n ] indicates the time range of historical data.

[0076] Based on the time period, the historical load data set D historical Segmented storage is performed, and each data set includes the load changes within a predetermined time period:

[0077] D historical-segmented (T) = {P(t i )|t i ∈[T0,T n ]}};

[0078] Among them, T0 and T0 represent the start time and end time of each specific time period respectively.

[0079] S102: Calculate the load fluctuation rate, resource utilization rate, and power loss rate of the distribution node based on the real-time operation data and historical load data of the distribution node.

[0080] In the embodiment of the present invention, the real-time operation data and historical load data of the distribution node are comprehensively analyzed to quantify the uncertainty and complexity of the distribution node and obtain uncertainty indicators. Specifically, the uncertainty indicators include the load fluctuation rate, resource utilization rate and power loss rate of the distribution node.

[0081] Exemplarily, in some embodiments of the present invention, the calculation formula for the load fluctuation rate of the power distribution node is:

[0082]

[0083] Among them, F var-combined (t,T) is the load fluctuation rate of the distribution node, P(t i ) is t i The real-time load value at the moment, P(T j ) is the time period T j The historical load value within To combine the load average of real-time and historical data, n and m are the total number of real-time data points and historical data points, respectively;

[0084] The resource utilization rate is calculated as follows:

[0085]

[0086] Among them, η combined (t,T) is the resource utilization of the distribution node, P out (t) and P in(t) respectively represent the output power and input power in the real-time operation data, P out (T) and P in (T) represents the output power and input power in the historical load data respectively;

[0087] The calculation formula of power loss rate is:

[0088]

[0089] Among them, L loss-combined (t,T) is the power loss rate of the distribution node.

[0090] S103, respectively calculating the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate, and the entropy value of the power loss rate.

[0091] In the embodiment of the present invention, the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate, and the entropy value of the power loss rate are calculated respectively.

[0092] Exemplarily, the calculation formula of the entropy value of the load fluctuation rate is:

[0093] H1=-∑F var-combined (t,T)log(F var-combined (t,T)

[0094] Among them, H1 is the entropy value of load fluctuation rate, F var-combined (t,T) is the load fluctuation rate of the distribution node;

[0095] The calculation formula of the entropy value of resource utilization is:

[0096] H2=-∑η combined (t,T)log(η combined (t,T)

[0097] Among them, H2 is the entropy value of resource utilization, η combined (t,T) is the resource utilization of the distribution node;

[0098] The calculation formula of the entropy value of the power loss rate is:

[0099] H3=-∑L loss-combined (t,T)log(L loss-combined (t,T)

[0100] Among them, H3 is the entropy value of the power loss rate, L loss-combined (t,T) is the power loss rate of the distribution node.

[0101] S104 , performing weighted summation on the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate, and the entropy value of the power loss rate to obtain a multi-dimensional entropy.

[0102] In the embodiment of the present invention, the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate and the entropy value of the power loss rate are weighted and summed to obtain the multi-dimensional entropy. The specific weighted summation formula is:

[0103] E entropy (t) = -w1·H1-w2·H2-w3·H3

[0104] Among them, E entropy (t) is the multidimensional entropy, w1, w2, and w3 are the weights of the entropy value of load fluctuation rate, the entropy value of resource utilization rate, and the entropy value of power loss rate, respectively.

[0105] S105. Predict the load of the distribution node based on historical load data and generate a load trend prediction function.

[0106] In the embodiment of the present invention, the load of the distribution node is predicted based on the historical load data, and a load trend prediction function is generated. The load trend prediction function can predict the load of the distribution node in a future period of time.

[0107] In some embodiments of the present invention, the process of generating a load trend prediction function is as follows:

[0108] 1. Perform multi-time scale decomposition on the segmented historical load data set to obtain historical load data at multiple time scales.

[0109] Exemplarily, the multi-time scale decomposition may adopt wavelet decomposition or empirical mode decomposition, which is not limited in the embodiment of the present invention.

[0110] 2. Extract the trend item T of historical load data at different time scales s (t) and the fluctuation term F s (t).

[0111] Trend Item T s (t) represents the long-term load change trend, which is extracted using low-frequency components or principal components. For example, the low-frequency components (approximate coefficients) in wavelet decomposition reflect the overall trend of the load.

[0112] Fluctuation term F s (t) represents the short-term load fluctuation characteristics, which are usually described by high-frequency components or noise parts. The detail coefficients in wavelet decomposition can be used to capture the short-term characteristics of load fluctuations.

[0113] 3. Based on the trend items and fluctuation items of the historical load data at different time scales, predict the predicted values ​​of the trend items and fluctuation items of the historical load data at different time scales at future moments.

[0114] Exemplarily, for trend items at the same time scale, multiple trend items are fitted to obtain a fitting function, and the predicted value of the trend item of the historical load data at the time scale at a future moment is predicted by the fitting function. Similarly, for fluctuation items at the same time scale, multiple fluctuation items are fitted to obtain a fitting function, and the predicted value of the fluctuation item of the historical load data at the time scale at a future moment is predicted by the fitting function.

[0115] 4. Calculate the multidimensional entropy of historical load data at different time scales.

[0116] In the embodiment of the present invention, the multidimensional entropy E of historical load data at different time scales is calculated. s . Multidimensional entropy E s The calculation process of can refer to the calculation process of the multidimensional entropy in the aforementioned embodiment, and the embodiments of the present invention will not be repeated here.

[0117] 5. Generate a load trend prediction function based on the multidimensional entropy of historical load data at different time scales and the predicted values ​​of trend items and fluctuation items of historical load data at different time scales in the future.

[0118] In the embodiment of the present invention, the uncertainty weights γ of each scale calculated by combining the multidimensional entropy theory are s , the trend items and fluctuation items of each scale are integrated to generate the load trend prediction curve. Uncertainty weight γ s The calculation formula is:

[0119]

[0120] Among them, E s Represents the multidimensional entropy corresponding to the Sth time scale.

[0121] The expression of the load trend prediction function is:

[0122]

[0123] Among them, C load-predict (t+Δt) is the predicted value of the load, S is the Sth time scale, E s is the multidimensional entropy of historical load data at the Sth time scale, is the predicted value of the trend item at the future moment, is the predicted value of the volatility term at future moments.

[0124] S106. Adaptively control the resource allocation ratio of the distribution nodes based on real-time operation data, load trend prediction function and multi-dimensional entropy.

[0125] In the embodiment of the present invention, the resource allocation ratio of the distribution node is adaptively regulated based on the real-time operation data, the load trend prediction function and the multi-dimensional entropy. The specific data expression is:

[0126]

[0127] Among them, M adaptive (t) is the resource allocation ratio at time t, α i , β i and γ i is the adaptive coefficient, E entropy (t) is the multidimensional entropy, D real-time (t) is the real-time operation data, C load-predict (t+Δt) is the predicted value of the load.

[0128] In some embodiments of the present invention, according to the generated load trend prediction function C load-predict (t+Δt), evaluate the potential load peak and fluctuation of each distribution node in advance, and identify the critical time point t where load abnormality may occur critical :

[0129] t critical ={t|C load-predict (t)≥P max-threshold}

[0130] Among them, P max-threshold is the preset load peak threshold. When the predicted load C load-predict (t) When this threshold is exceeded, it indicates that the distribution node may face overload risk and resource scheduling and regulation need to be carried out in advance.

[0131] The power grid resource optimization method based on multidimensional entropy theory provided by the present invention obtains real-time operation data and historical load data of each distribution node in the distribution network, calculates the load fluctuation rate, resource utilization rate and electric energy loss rate of the distribution node based on the real-time operation data and historical load data of the distribution node, calculates the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate and the entropy value of the electric energy loss rate respectively, performs weighted summation on the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate and the entropy value of the electric energy loss rate to obtain multidimensional entropy, predicts the load of the distribution node based on the historical load data, generates a load trend prediction function, adaptively adjusts the resource allocation ratio of the distribution node based on the real-time operation data, the load trend prediction function and the multidimensional entropy, quantitatively analyzes the uncertainty of the power grid system based on the multidimensional entropy theory, and adaptively adjusts the resource allocation ratio of the distribution node to achieve dynamic load balancing and optimal resource configuration of each distribution node.

[0132] Figure 2 A schematic diagram of the structure of a power grid resource optimization device based on multidimensional entropy theory provided by the present invention, such as Figure 2 As shown, the power grid resource optimization device based on multi-dimensional entropy theory includes:

[0133] The data acquisition module 201 is used to acquire the real-time operation data and historical load data of each distribution node in the distribution network;

[0134] An uncertainty index calculation module 202, configured to calculate the load fluctuation rate, resource utilization rate and power loss rate of the distribution node based on the real-time operation data and the historical load data of the distribution node;

[0135] An entropy value calculation module 203, used to respectively calculate the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate and the entropy value of the power loss rate;

[0136] A weighted summation module 204 is used to perform weighted summation on the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate, and the entropy value of the power loss rate to obtain a multi-dimensional entropy;

[0137] A load prediction function generating module 205, configured to predict the load of the distribution node based on the historical load data and generate a load trend prediction function;

[0138] The resource allocation control module 206 adaptively controls the resource allocation ratio of the distribution node based on the real-time operation data, the load trend prediction function and the multi-dimensional entropy.

[0139] In some embodiments of the present invention, the calculation formula of the load fluctuation rate of the power distribution node is:

[0140]

[0141] Among them, F var-combined (t,T) is the load fluctuation rate of the distribution node, P(t i ) is t i The real-time load value at the moment, P(T j ) is the time period T j The historical load value within To combine the load average of real-time and historical data, n and m are the total number of real-time data points and historical data points, respectively;

[0142] The calculation formula of the resource utilization is:

[0143]

[0144] Among them, η combined (t,T) is the resource utilization of the distribution node, P out (t) and P in (t) respectively represent the output power and input power in the real-time operation data, Pout (T) and P in (T) represents the output power and input power in the historical load data respectively;

[0145] The calculation formula of the power loss rate is:

[0146]

[0147] Among them, L loss-combined (t,T) is the power loss rate of the distribution node.

[0148] In some embodiments of the present invention, the calculation formula of the entropy value of the load fluctuation rate is:

[0149] H1=-∑F var-combined (t,T)log(F var-combined (t,T)

[0150] Among them, H1 is the entropy value of load fluctuation rate, F var-combined (t,T) is the load fluctuation rate of the distribution node;

[0151] The calculation formula of the entropy value of the resource utilization is:

[0152] H2=-∑η combined (t,T)log(η combined (t,T)

[0153] Among them, H2 is the entropy value of resource utilization, η combined (t,T) is the resource utilization of the distribution node;

[0154] The calculation formula of the entropy value of the power loss rate is:

[0155] H3=-∑L loss-combined (t,T)log(L loss-combined (t,T)

[0156] Among them, H3 is the entropy value of the power loss rate, L loss-combined (t,T) is the power loss rate of the distribution node.

[0157] In some embodiments of the present invention, the load prediction function generation module 205 includes:

[0158] A decomposition submodule, used for performing multi-time-scale decomposition on the historical load data to obtain historical load data of multiple time scales;

[0159] An extraction submodule, used for extracting trend items and fluctuation items of the historical load data at different time scales;

[0160] A prediction submodule, used for predicting the predicted values ​​of the trend items and fluctuation items of the historical load data at different time scales at future moments based on the trend items and fluctuation items of the historical load data at different time scales;

[0161] The multidimensional entropy calculation submodule is used to calculate the multidimensional entropy of the historical load data at different time scales; the prediction function generation submodule is used to generate a load trend prediction function based on the multidimensional entropy of the historical load data at different time scales and the predicted values ​​of the trend items and fluctuation items of the historical load data at different time scales in the future.

[0162] In some embodiments of the present invention, the expression of the load trend prediction function is:

[0163]

[0164] Among them, C load-predict (t+Δt) is the predicted value of the load, S is the Sth time scale, E s is the multidimensional entropy of the historical load data at the Sth time scale, is the predicted value of the trend item at the future moment, is the predicted value of the volatility term at future moments.

[0165] In some embodiments of the present invention, the mathematical expression for adaptively regulating the resource allocation ratio of the power distribution node based on the real-time operation data, the load trend prediction function and the multi-dimensional entropy is:

[0166]

[0167] Among them, M adaptive (t) is the resource allocation ratio at time t, α i , β i and γ i is the adaptive coefficient, E entropy (t) is the multidimensional entropy, D real-time (t) is the real-time operation data, C load-predict (t+Δt) is the predicted value of the load.

[0168] In some embodiments of the present invention, the power grid resource optimization device based on multi-dimensional entropy theory further includes:

[0169] A judgment module, used to judge whether the predicted value of the load reaches a load peak threshold;

[0170] The scheduling module is used to perform resource scheduling and regulation in advance when the predicted value of the load reaches the load peak threshold.

[0171] The above-mentioned power grid resource optimization device based on multidimensional entropy theory can execute the power grid resource optimization method based on multidimensional entropy theory provided by the aforementioned embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the power grid resource optimization method based on multidimensional entropy theory.

[0172] Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0173] like Figure 3 As shown, the electronic device includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0174] A number of components in the electronic device are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0175] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a power grid resource optimization method based on multidimensional entropy theory.

[0176] In some embodiments, the power grid resource optimization method based on multidimensional entropy theory can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the power grid resource optimization method based on multidimensional entropy theory described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the power grid resource optimization method based on multidimensional entropy theory in any other appropriate manner (for example, by means of firmware).

[0177] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0178] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0179] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0180] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0181] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0182] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0183] An embodiment of the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements a power grid resource optimization method based on multi-dimensional entropy theory as provided in any embodiment of the present application.

[0184] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0185] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0186] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for optimizing power grid resources based on multidimensional entropy theory, characterized in that: include: Obtain real-time operation data and historical load data of each distribution node in the distribution network; Calculate the load fluctuation rate, resource utilization rate and power loss rate of the power distribution node based on the real-time operation data and the historical load data of the power distribution node; respectively calculating the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate, and the entropy value of the power loss rate; A weighted summation of the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate, and the entropy value of the power loss rate is performed to obtain a multidimensional entropy; Predicting the load of the power distribution node based on the historical load data, and generating a load trend prediction function; The resource allocation ratio of the power distribution node is adaptively regulated based on the real-time operation data, the load trend prediction function and the multi-dimensional entropy.

2. The power grid resource optimization method based on multidimensional entropy theory according to claim 1 is characterized in that: The calculation formula of the load fluctuation rate of the distribution node is: Among them, F var-combined (t,T) is the load fluctuation rate of the distribution node, P(t i ) is t i The real-time load value at the moment, P(T j ) is the time period T j The historical load value within To combine the load average of real-time and historical data, n and m are the total number of real-time data points and historical data points, respectively; The calculation formula of the resource utilization is: Among them, η combined (t,T) is the resource utilization of the distribution node, P out (t) and P in (t) respectively represent the output power and input power in the real-time operation data, P out (T) and P in (T) represents the output power and input power in the historical load data respectively; The calculation formula of the power loss rate is: Among them, L loss-combined (t,T) is the power loss rate of the distribution node.

3. The power grid resource optimization method based on multidimensional entropy theory according to claim 1 is characterized in that: The calculation formula of the entropy value of the load fluctuation rate is: H1=-∑F var-combined (t,T)log(F var-combined (t,T)) Among them, H1 is the entropy value of load fluctuation rate, F var-combined (t,T) is the load fluctuation rate of the distribution node; The calculation formula of the entropy value of the resource utilization is: H2=-∑η combined (t,T)log(η combined (t,T)) Among them, H2 is the entropy value of resource utilization, η combined (t,T) is the resource utilization of the distribution node; The calculation formula of the entropy value of the power loss rate is: H3=-∑L loss-combined (t,T)log(L loss-combined (t,T)) Among them, H3 is the entropy value of the power loss rate, L loss-combined (t,T) is the power loss rate of the distribution node.

4. The power grid resource optimization method based on multidimensional entropy theory according to claim 1 is characterized in that: Predicting the load of the power distribution node based on the historical load data and generating a load trend prediction function, including: Decomposing the historical load data at multiple time scales to obtain historical load data at multiple time scales; Extracting trend items and fluctuation items of the historical load data at different time scales; Based on the trend items and fluctuation items of the historical load data at different time scales, predict the predicted values ​​of the trend items and fluctuation items of the historical load data at different time scales at future moments; Calculating multidimensional entropy of the historical load data at different time scales; A load trend prediction function is generated based on the multidimensional entropy of the historical load data at different time scales and the predicted values ​​of the trend item and the fluctuation item of the historical load data at different time scales at future moments.

5. The power grid resource optimization method based on multidimensional entropy theory according to claim 4 is characterized in that: The expression of the load trend prediction function is: Among them, C load-predict (t+Δt) is the predicted value of the load, S is the Sth time scale, E s is the multidimensional entropy of the historical load data at the Sth time scale, is the predicted value of the trend item at the future moment, is the predicted value of the volatility term at future moments.

6. The power grid resource optimization method based on multidimensional entropy theory according to claim 1 is characterized in that: The mathematical expression for adaptively regulating the resource allocation ratio of the power distribution node based on the real-time operation data, the load trend prediction function and the multi-dimensional entropy is: Among them, M adaptive (t) is the resource allocation ratio at time t, α i , β i and γ i is the adaptive coefficient, E entropy (t) is the multidimensional entropy, D real-time (t) is the real-time operation data, C load-predict (t+Δt) is the predicted value of the load.

7. The power grid resource optimization method based on multidimensional entropy theory according to claim 1 is characterized in that: Also includes: Determining whether the predicted value of the load reaches a load peak threshold; If so, resource scheduling and regulation should be carried out in advance.

8. A power grid resource optimization device based on multidimensional entropy theory, characterized in that: include: A data acquisition module is used to obtain real-time operation data and historical load data of each distribution node in the distribution network; An uncertainty index calculation module, used to calculate the load fluctuation rate, resource utilization rate and power loss rate of the distribution node based on the real-time operation data and the historical load data of the distribution node; An entropy value calculation module, used to respectively calculate the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate and the entropy value of the power loss rate; A weighted summation module, used for weighted summation of the entropy value of the load fluctuation rate, the entropy value of the resource utilization rate and the entropy value of the power loss rate to obtain a multi-dimensional entropy; A load prediction function generating module, used to predict the load of the distribution node based on the historical load data and generate a load trend prediction function; A resource allocation control module adaptively controls the resource allocation ratio of the distribution node based on the real-time operation data, the load trend prediction function and the multi-dimensional entropy.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the power grid resource optimization method based on multi-dimensional entropy theory as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a power grid resource optimization method based on multi-dimensional entropy theory as described in any one of claims 1 to 7 is implemented.

Images