Multi-energy regional autonomous optimization regulation and control method for virtual micro-grid regulation and control

Abstract

The invention discloses a multi-energy area autonomous optimization regulation and control method oriented to virtual micro-grid regulation and control, and particularly relates to the technical field of power system optimization regulation and control. The regulation and control method comprises the steps that corresponding data are collected, a virtual micro-grid serves as a basic unit, a topological structure based on energy transmission is established, and the virtual micro-grid serves as the basic unit; meanwhile, a contact relation is established between different virtual micro-grid units; constructing a parallel energy supply scene, then establishing a corresponding evaluation function based on the equivalent power transmission power in combination with the actual power transmission power and in combination with the state of each region, and solving by using an MOEDO algorithm to avoid falling into a local optimal solution so as to obtain a corresponding scheduling strategy; according to the multi-energy regional autonomous optimization regulation and control method oriented to virtual micro-grid regulation and control, firstly, a regional virtual micro-grid definition is given through polymorphic energy transmission, and an energy transmission means is normalized as a virtual contact definition, so that the problem of energy transmission in other forms among different regions is solved.

Description

Technical Field

[0001] The present application relates to the technical field of power system optimization and control, and more specifically, to a multi-energy regional autonomous optimization and control method for virtual microgrid control. Background Art

[0002] With the advancement of new energy and environmental protection policies, more and more distributed clean energy and energy-saving technologies have been widely promoted. Most distributed clean energy and energy-saving loads reflect relatively concentrated characteristics, such as being widely used in industrial, commercial, residential and other parks. It is difficult to optimize and regulate multiple energies in a single park, and due to the differences in demand and supply between multiple parks, mutual cooperation and support are more needed. Therefore, how to achieve the optimization and regulation of multiple energy sources across parks, that is, the autonomous optimization and regulation of multi-energy regions, has important research significance and application value.

[0003] Therefore, to address the above issues, a multi-energy regional autonomous optimization control method for virtual microgrid control is proposed. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present application provides a multi-energy regional autonomous optimization control method for virtual microgrid control to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above objectives, the present application provides the following technical solutions: a multi-energy regional autonomous optimization control method for virtual microgrid control, the control method steps are:

[0006] Collect corresponding data and build the optimal function to measure the target of each node virtual microgrid according to actual needs;

[0007] Taking the virtual microgrid as the basic unit, a topological structure based on energy transmission is established. At the same time, a communication relationship is established between different virtual microgrid units, and then the actual non-electric energy transmission is virtualized into actual electric energy transmission through intentional energy.

[0008] Constructing parallel energy supply scenarios: Constructing a set of energy consumption data for each virtual microgrid without virtual connection, which is only powered by the grid and exchanges energy with other virtual microgrids in each period;

[0009] Then, based on the equivalent power transmission power combined with the actual power transmission power and the status of each area, a corresponding evaluation function is established. Each park generates a corresponding objective function, and the MOEDO algorithm is used to solve it to avoid falling into the local optimal solution and obtain the corresponding scheduling strategy.

[0010] Furthermore, the virtual microgrid is a regional complex that is relatively independent at the electric energy level and has multiple energy types.

[0011] Furthermore, the parallel energy supply scenario is divided into a constant part and a variable part, and they are measured separately, wherein the constant part is a relatively fixed plan for energy consumption in the virtual microgrid area at each time scale within the day; the variable part is a physical modeling of the energy channel, which is a highly random energy pathway for transportation pipelines or mobile energy storage vehicles that does not change according to time periods.

[0012] Furthermore, the unchanged part of the parallel energy supply scenario first collects energy supply data: the data of 100 data points within the standard 365 days of each regional virtual microgrid are obtained to obtain the corresponding data set P:

[0013] P=[P ij ](i=0,1,2,…100; j=0,1,2,…365),

[0014] Among them, P ij is the node power usage in any time period,

[0015]

[0016] Where P l The time period power of the main energy unit or micro-node in the node is introduced as W lall is the energy consumption of other non-electric energy units, t all is the total output time of the energy unit, P avg is the average power of renewable energy in the region, P plant is the power generation capacity of the power plants in the region, P G Provide power to the grid side;

[0017] The data is then processed on a pan-time scale.

[0018] By fitting the power change through the time scale, the time scale of the power peak area with large power change is described as:

[0019] During the peak power consumption period, the power description collection can collect all data points; when the fluctuation size δ of the data point is greater than the specified value, the same treatment is performed, and the specified value is:

[0020]

[0021] For data point homogeneity or power valleys, reduction processing is performed to obtain the final actual data set P':

[0022] P'=[P ij ](i=0,1,2,…n; j=0,1,2,…365,n<100),

[0023] Then, based on the fitting process of PeepholeLSTM, the obtained data set is further processed, and the corresponding power prediction fitting is performed by using PeepholeLSTM to obtain the power data curve reflecting the characteristics of the region:

[0024] f t =σ(W f ·[C t-1 ,h t-1 ,x t ]+b f )

[0025] i t =σ(W i ·[C t-1 ,h t-1 ,x t ]+b i )

[0026] o t =σ(W o ·[C t ,h t-1 ,x t ]+b o )

[0027]

[0028] Integrate P' into x t Input the form, train the model accordingly and find the corresponding weight matrix W f , W i , W o , W (c) ,b f ,b i ,b o And until the model obtains the ideal data set h (t) .

[0029] Furthermore, the variable part of the parallel energy supply scenario first establishes a mobile energy storage energy supply channel.

[0030] Specifically, the corresponding energy transfer function is established:

[0031]

[0032] The state of charge of the mobile energy storage vehicle is SOC i , the number of mobile energy storage vehicles that can be called is sum, and the path length of all energy storage vehicles from the area is l i ;

[0033] Other non-periodic energy transmission changes, for energy channels with strong inertia, have daily planned changes or temporary sudden changes, and become non-periodic, align and collect corresponding data to obtain a time-independent data sequence P t , do exponential averaging, specifically:

[0034] v t =βP t +(1-β)v t-1 ,

[0035] The corresponding sequence data v is obtained t , the sequence data is coupled with the previous time dimension data according to the actual situation, so that the final output sequence data takes into account both the actual power consumption of the region and the actual energy transmission capacity of the region from the power level.

[0036] Furthermore, in the parallel energy supply scenario, the constant part and the variable part need to be accumulated and coupled, and the power of the constant part and the variable part need to be accumulated and coupled to obtain the final actual transmission power. The coupling weight is repeatedly obtained by regression, and finally the power time series within the day is output.

[0037] P ij =W con ⊙P'+W var ⊙P var ,

[0038] The actual electric power for energy exchange between regions is obtained, and the actual energy transmission situation is replaced by the power transmission of the power line with an unconstant intra-day multi-point curve.

[0039] Technical effects and advantages of this application:

[0040] 1. Compared with the existing technology, this multi-energy regional autonomous optimization control method for virtual microgrid control first gives the regional virtual microgrid definition through polymorphic energy transmission, and standardizes the energy transmission means as a virtual connection definition, thereby solving other forms of energy transmission problems between different regions.

[0041] 2. Compared with the existing technology, this multi-energy regional autonomous optimization control method for virtual microgrid control is used to accurately describe the power transmission situation of the power interconnection line. It performs result-oriented power metering by quantifying the specific situation of transmission using actual energy size, and finely classifies the properties of the power transmission source into variable and constant parts, and couples them accordingly to obtain the final pseudo-power interconnection line transmission power.

[0042] 3. Compared with the existing technology, this multi-energy regional autonomous optimization control method for virtual microgrid control combines power information and park energy consumption, involves an evaluation function to form an optimal function for park control, forms a multi-objective optimization problem, and obtains the optimal control means by solving the problem. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a schematic diagram of the process of the control method of this application;

[0044] Figure 2 This is a schematic diagram of the fitting process based on PeepholeLSTM in this application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0046] Example

[0047] This application first defines three definitions, namely, the definition of virtual microgrid, the definition of virtual connection and the definition of pseudo-electric long-distance control. The definition of virtual microgrid is to virtualize the concept of microgrid through the concept of virtual energy channel, and regard regional complexes that are relatively independent at the electric energy level and have multiple forms of energy as nominal "virtual microgrids". The specific definition conditions are given below:

[0048] (1) The virtual microgrid must first be supplied with electricity directly or indirectly by the grid;

[0049] (2) There should be no corresponding power transmission paths between virtual microgrids, or the scale of power transmission between virtual microgrids is almost negligible compared to the regional power consumption scale;

[0050] (3) The virtual microgrid must be of a relatively large scale, making it necessary for it to participate in regulation;

[0051] (4) The virtual microgrid should have polymorphic energy units, that is, the ability to generate or transmit non-electric energy;

[0052] (5) Virtual microgrids should have the ability to exchange energy through non-electrical energy transmission.

[0053] By introducing the above constraints, the specific concept of the virtual microgrid is actually defined and described. The following regulation or scheduling is based on the above basic definition units.

[0054] The definition of virtual connection is based on the virtual microgrid as the basic unit, and a topological structure based on energy transmission is established. Therefore, a connection relationship is established between different virtual microgrid units. At the same time, the intention energy virtualizes the actual non-electric energy transmission into actual electric energy transmission, so as to integrate it into the overall regulation and make the regulation more capable of having its corresponding basis. The specific definition conditions are:

[0055] (1) Virtual communication is established based on actual non-electric energy transmission, and its specific methods include but are not limited to hydraulic potential energy transmission, oil and gas energy transmission, mobile energy transmission, etc.;

[0056] (2) Virtual connection is equivalent to the corresponding power transmission. The calculation of the amount of energy transmission and the actual amount of energy replacement is equivalent to the actual power connection line established between different virtual microgrids for transmission.

[0057] (3) Virtual interconnection is not completely the same as traditional power interconnection line transmission. The energy transmission carried out by virtual interconnection does not have the electrical characteristics of traditional power transmission and does not have power flow;

[0058] (4) Virtual connections are highly variable and change in real time according to the actual conditions of the actual transmission energy. They are time-specific and not constant.

[0059] Through the above definition conditions, we point out that virtual connection is actually a pseudo-electric channel that is equivalent to the effect of power connection line through the transmission and exchange of polymorphic energy (other forms of energy) between virtual microgrids. By defining the virtual microgrids, i.e. nodes in the topological structure, and the virtual connections, i.e. branches, between virtual microgrids, a target structure for regulation is established. Therefore, the regulated target structure is clear and defined at the power transmission level.

[0060] The definition of pseudo-electric long-distance regulation is that after having the target to be adjusted, according to the actual needs of different regions and the non-electric energy transmission capacity, in the established network structure, regulation is carried out from the relevant perspectives of electric energy regulation, so that the virtual microgrid area can finally achieve the optimal value from multiple perspectives such as energy consumption cost, carbon emission cost, and energy margin. Therefore, the definition of pseudo-electric long-distance regulation is: that is, through the planning of polymorphic energy transmission of different "virtual microgrids", the optimization regulation equivalent to the electric energy level is produced, even if there is no actual power transmission between the two areas under regulation.

[0061] As attached Figure 1 to Figure 2 A multi-energy regional autonomous optimization control method for virtual microgrid control is shown, and the control method steps are:

[0062] Collect corresponding data and build the optimal function to measure the target of each node virtual microgrid according to actual needs;

[0063] Taking the virtual microgrid as the basic unit, a topological structure based on energy transmission is established. At the same time, a communication relationship is established between different virtual microgrid units, and then the actual non-electric energy transmission is virtualized into actual electric energy transmission through intentional energy.

[0064] Constructing parallel energy supply scenarios: Constructing a set of energy consumption data for each virtual microgrid without virtual connection, which is only powered by the grid and exchanges energy with other virtual microgrids in each period;

[0065] Then, based on the equivalent power transmission power combined with the actual power transmission power and the status of each area, a corresponding evaluation function is established. Each park generates a corresponding objective function, and the MOEDO algorithm is used to solve it to avoid falling into the local optimal solution and obtain the corresponding scheduling strategy.

[0066] Virtual microgrids are regional complexes that are relatively independent at the electrical energy level and have multiple forms of energy.

[0067] The parallel energy supply scenario is divided into a constant part and a variable part, and they are measured separately. The constant part is a relatively fixed plan for energy consumption in the virtual microgrid area at each time scale within the day; the variable part is a physical modeling of the energy channel, which is a highly random energy pathway for transportation pipelines or mobile energy storage vehicles that does not change according to time periods.

[0068] The unchanged part of the parallel energy supply scenario first collects energy supply data: the data of 100 data points within the standard 365 days of each regional virtual microgrid are obtained to obtain the corresponding data set P:

[0069] P=[P ij ](i=0,1,2,…100; j=0,1,2,…365),

[0070] Among them, P ij is the node power usage in any time period,

[0071]

[0072] Where P l The time period power of the main energy unit or micro-node in the node is introduced as W lall is the energy consumption of other non-electric energy units, t all is the total output time of the energy unit, P avg is the average power of renewable energy in the region, P plant is the power generation capacity of the power plants in the region, P G Provide power to the grid side;

[0073] The data is then processed on a pan-time scale.

[0074] By fitting the power change through the time scale, the time scale of the power peak area with large power change is described as:

[0075] During the peak power consumption period, the power description collection can collect all data points; when the fluctuation size δ of the data point is greater than the specified value, the same treatment is performed, and the specified value is:

[0076]

[0077] For data point homogeneity or power valleys, reduction processing is performed to obtain the final actual data set P':

[0078] P'=[P ij ](i=0,1,2,…n; j=0,1,2,…365,n<100),

[0079] Then, based on the fitting process of PeepholeLSTM, the obtained data set is further processed, and the corresponding power prediction fitting is performed by using PeepholeLSTM to obtain the power data curve reflecting the characteristics of the region:

[0080] f t =σ(W f ·[C t-1 ,h t-1 ,x t ]+b f )

[0081] i t =σ(W i ·[C t-1 ,h t-1 ,x t ]+b i )

[0082] o t =σ(W o ·[C t ,h t-1 ,x t ]+b o )

[0083]

[0084] Integrate P' into x t Input the form, train the model accordingly and find the corresponding weight matrix W f , W i , W o , W (c) ,b f ,b i ,bo And until the model obtains the ideal data set h (t) .

[0085] The variable part of the parallel energy supply scenario first establishes a mobile energy storage supply channel.

[0086] Specifically, the corresponding energy transfer function is established.

[0087]

[0088] The state of charge of the mobile energy storage vehicle is SOC i , the number of mobile energy storage vehicles that can be called is sum, and the path length of all energy storage vehicles from the area is l i ;

[0089] Other non-periodic energy transmission changes, for energy channels with strong inertia, have daily planned changes or temporary sudden changes, and become non-periodic, align and collect corresponding data to obtain a time-independent data sequence P t , do exponential averaging, specifically:

[0090] v t =βP t +(1-β)v t-1 ,

[0091] The corresponding sequence data v is obtained t , the sequence data is coupled with the previous time dimension data according to the actual situation, so that the final output sequence data takes into account both the actual power consumption of the region and the actual energy transmission capacity of the region from the power level.

[0092] In the parallel energy supply scenario, the constant part and the variable part need to be accumulated and coupled. The power of the constant part and the variable part need to be accumulated and coupled to obtain the final actual transmission power. The coupling weight is repeatedly obtained through regression, and the power time series within the day is finally output.

[0093] P ij =W con ⊙P'+W var ⊙P var ,

[0094] The actual electric power for energy exchange between regions is obtained, and the actual energy transmission situation is replaced by the power transmission of the power line with an unconstant intra-day multi-point curve.

[0095] According to the actual situation of the region, the following measurement indicators are proposed as variables of the objective function:

[0096] (1) Actual utilization rate of new energy equipment, the actual situation of new energy equipment output accounting for actual use or power flow α:

[0097]

[0098] (2) The proportion of virtual contact energy transmission in the peak period of regional electricity consumption β:

[0099]

[0100] (3) Energy consumption of the park from the grid side P iG :

[0101] P iG =P i -P ij

[0102] Therefore, the target problem to be solved is:

[0103]

[0104] By solving this problem, the corresponding energy allocation plan is obtained. Under the condition of satisfying the virtual connection constraints, each virtual microgrid can obtain less electricity from the grid side and use electricity converted from new energy as much as possible, while ensuring that it can meet the load demand at peak times.

Claims

1. A multi-energy regional autonomous optimization control method for virtual microgrid control, characterized by: The steps of the control method are: Collect corresponding data and build the objective function to measure the virtual microgrid of each node according to actual needs; Taking the virtual microgrid as the basic unit, a topological structure based on energy transmission is established. At the same time, a communication relationship is established between different virtual microgrid units, and then the actual non-electric energy transmission is virtualized into actual electric energy transmission through intentional energy. Constructing parallel energy supply scenarios: Constructing a set of energy consumption data for each virtual microgrid without virtual connection, which is only powered by the grid and exchanges energy with other virtual microgrids in each period; Then, based on the equivalent power transmission power combined with the actual power transmission power and the status of each area, a corresponding evaluation function is established. Each park generates a corresponding objective function, and the MOEDO algorithm is used to solve it to avoid falling into the local optimal solution and obtain the corresponding scheduling strategy.

2. The multi-energy regional autonomous optimization control method for virtual microgrid control according to claim 1 is characterized by: The virtual microgrid is a regional complex that is relatively independent at the electric energy level and has multiple forms of energy.

3. The multi-energy regional autonomous optimization control method for virtual microgrid control according to claim 1 is characterized by: The parallel energy supply scenario is divided into a constant part and a variable part, and they are measured separately. The constant part is a relatively fixed plan for energy consumption in the virtual microgrid area at each time scale within the day; the variable part is a physical modeling of the energy channel, which is a highly random energy path for transportation pipelines or mobile energy storage vehicles that does not change according to time periods.

4. The multi-energy regional autonomous optimization control method for virtual microgrid control according to claim 3 is characterized by: The unchanged part of the parallel energy supply scenario first collects energy supply data: the data of 100 data points within the standard 365 days of each regional virtual microgrid are obtained to obtain the corresponding data set P: P=[P ij ](i=0,1,2,…100;j=0,1,2,…365), Among them, P ij is the node power usage in any time period, Where P l The time period power of the main energy unit or micro-node in the node is introduced as W lall is the energy consumption of other non-electric energy units, t all is the total output time of the energy unit, P avg is the average power of renewable energy in the region, P plant is the power generation capacity of the power plants in the region, P G Provide power to the grid side; The data is then processed on a pan-time scale. By fitting the power change through the time scale, the time scale of the power peak area with large power change is described as: During the peak power consumption period, the power description collection can collect all data points; when the fluctuation size δ of the data point is greater than the specified value, the same treatment is performed, and the specified value is: For data point homogeneity or power valleys, reduction processing is performed to obtain the final actual data set P': P'=[P ij ](i=0,1,2,…n;j=0,1,2,…365,n<100), Then, based on the fitting process of PeepholeLSTM, the obtained data set is further processed, and the corresponding power prediction fitting is performed by using PeepholeLSTM to obtain the power data curve reflecting the characteristics of the region: f t =σ(W f ·[C t-1 ,h t-1 ,x t ]+b f ) i t =σ(W i ·[C t-1 ,h t-1 ,x t ]+b i ) o t =σ(W o ·[C t ,h t-1 ,x t ]+b o ) Integrate P' into x t Input the form, train the model accordingly and find the corresponding weight matrix W f , W i , W o , W (c) ,b f ,b i ,b o And until the model obtains the ideal data set h (t) .

5. The multi-energy regional autonomous optimization control method for virtual microgrid control according to claim 4 is characterized in that: The variable part of the parallel energy supply scenario first establishes a mobile energy storage supply channel. Specifically, the corresponding energy transfer function is established: The state of charge of the mobile energy storage vehicle is SOC i , the number of mobile energy storage vehicles that can be called is sum, and the path length of all energy storage vehicles from the area is l i ; Other non-periodic energy transmission changes, for energy channels with strong inertia, have daily planned changes or temporary sudden changes, and become non-periodic, align and collect corresponding data to obtain a time-independent data sequence P t , do exponential averaging, specifically: in t =βP t +(1-β)v t-1 , The corresponding sequence data v is obtained t , the sequence data is coupled with the previous time dimension data according to the actual situation, so that the final output sequence data takes into account both the actual power consumption of the region and the actual energy transmission capacity of the region from the power level.

6. The multi-energy regional autonomous optimization control method for virtual microgrid control according to claim 5 is characterized by: In the parallel energy supply scenario, the constant part and the variable part need to be accumulated and coupled, and the actual transmission power is obtained by accumulating and coupling the power of the constant part and the variable part. The coupling weight is repeatedly obtained by regression, and the power time series within the day is finally output. P ij =W con ⊙P'+W var ⊙P var , The actual electric power for energy exchange between regions is obtained, and the actual energy transmission situation is replaced by the power transmission of the power line with an unconstant intra-day multi-point curve.

Images