High-energy-consumption industrial load multi-target autonomous optimization adjustment system and method and storage medium

Abstract

The invention discloses a high-energy-consumption industrial load multi-target autonomous optimization adjustment system and method and a storage medium, and the method comprises the steps: optimizing and adjusting a production process according to the energy consumption data of the production process and the preset value of the real-time carbon emission data of equipment, and obtaining the power grid power demand of the used equipment according to the optimized production process; the method comprises the following steps: by taking the power grid power demand of equipment as a balance constraint and the minimum power generation cost per hour as a target function, allocating the power grid power demand of the equipment according to the power of each aggregation region at each moment and the cost of the aggregation region, and then, by taking the allocated power grid power demand of each aggregation region as the balance constraint, allocating the power grid power demand of each aggregation region; and by taking the lowest power generation cost of each aggregation region as a target function, redistributing the power grid power demand of each aggregation region after distribution. According to the method, the power consumption demand is accurately predicted through accurate extraction and clustering of the load characteristics, so that the energy consumption cost is reduced, and meanwhile, carbon emission and pollution are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent power consumption, and particularly to a multi-objective autonomous optimization regulation system and method for high-energy-consuming industrial loads and a storage medium, and more particularly to a multi-objective autonomous optimization regulation system and method for high-energy-consuming industrial loads considering carbon emission constraints and a storage medium. Background Art

[0002] High-energy-consuming industries, including industries such as iron and steel, cement, and electrolytic aluminum, are important components of the national economy and one of the main sources of global energy consumption. The production processes of these industries are complex and involve a large amount of energy input, thus becoming a key area for countries to achieve energy conservation and emission reduction goals. Understanding their main technological processes and corresponding energy consumption characteristics is of great significance for optimizing production processes, improving energy efficiency, and reducing carbon emissions.

[0003] Iron and steel production mainly includes the following key processes: sintering, ironmaking, steelmaking, continuous casting, and rolling. In the sintering process, raw materials such as iron ore powder and coke are sintered at high temperature to form sintered ore for subsequent use; ironmaking is the reaction of iron ore and coke in a blast furnace to produce pig iron, and the whole process requires a large amount of coke and high-temperature gas to provide chemical energy; next, the steelmaking process converts pig iron into steel, which requires removing excessive carbon and other impurities through equipment such as converters and electric furnaces, and also requires a large amount of electricity and oxygen; continuous casting and rolling are the processes of further processing molten steel into steel products, and the energy consumption is mainly concentrated in the power consumption of rolling equipment and the heating process.

[0004] Cement production generally includes several main processes such as raw material preparation, calcination, cooling, and grinding. First is the raw material preparation stage, which involves crushing, screening, and mixing of raw materials such as limestone and clay, and the energy consumption in this process is concentrated in the power consumption of mechanical equipment; the calcination process is the core of cement production, and raw materials such as limestone are decomposed and chemically reacted in a high-temperature kiln to form clinker, and this process requires a large amount of fuel (such as coal or natural gas) combustion to provide high temperature; the clinker needs to be quickly cooled after calcination, and the cooling process usually relies on air or water cooling systems, and the cooling energy consumption cannot be ignored; finally, the grinding process grinds the cooled clinker together with a certain proportion of additives such as gypsum into cement powder, and the energy consumption in this stage mainly comes from the power consumption of the mill.

[0005] The production of electrolytic aluminum uses electrolytic cells as the core equipment, mainly including three main steps: raw material preparation, electrolysis, and aluminum liquid casting. In the raw material preparation stage, bauxite, carbon materials, etc. enter the electrolytic cell after being crushed, screened, and mixed; in the electrolytic cell, a large amount of electrical energy is used to reduce alumina to aluminum metal, and the energy consumption in the electrolysis process is extremely huge, usually being the largest energy consumption source in the electrolytic aluminum industry; after electrolysis is completed, the aluminum liquid needs to be cast and cooled to finally form aluminum ingots or other aluminum products, and the energy consumption of heating and cooling is also involved in the casting process.

[0006] In summary, the production processes of high-energy-consuming industries such as steel, cement, and electrolytic aluminum are different, but all involve a large amount of energy consumption, and the various processes are closely linked. At present, the load characteristics of high-energy-consuming industrial users are mainly extracted by traditional statistical methods, which cannot accurately reflect the load change law and response characteristics. Therefore, it is difficult for users to optimize the operation strategy of the production equipment of high-energy-consuming industries by identifying energy consumption peaks, making it difficult to achieve carbon emission compliance, with low energy utilization efficiency and high energy consumption costs at the same time. Summary of the Invention

[0007] The object of the present invention is to propose a multi-objective autonomous optimization regulation system and method for high-energy-consuming industrial loads and a storage medium in view of the lack of intelligent analysis means in the existing methods for extracting the load characteristics of high-energy-consuming industrial users. The present invention is based on a load characteristic extraction method driven by big data analysis and machine learning models, which can accurately predict electricity demand through the precise extraction and clustering of load characteristics, and real-time regulate the device power, thereby significantly improving energy utilization efficiency, reducing energy consumption costs, and at the same time reducing carbon emissions and pollution.

[0008] To achieve this object, a multi-objective autonomous optimization regulation system for high-energy-consuming industrial loads designed in the first aspect of the present invention includes an energy consumption and operation parameter acquisition module, a carbon emission analysis module, and a two-layer optimization scheduling module; the energy consumption and operation parameter acquisition module is used to obtain the energy consumption data of the production process and the real-time operation power data of the equipment used in this production process; the carbon emission analysis module obtains the real-time carbon emission data of the equipment used in the production process according to the real-time operation power data of the equipment and the carbon emission factor; the two-layer optimization scheduling module adjusts the production process to make the energy consumption data of the production process and the real-time carbon emission data of the equipment reach preset values, and obtains the grid power demand of the equipment used in the adjusted production process; taking the grid power demand of the equipment as the balance constraint and the lowest power generation cost set by the aggregator during the set period as the objective function, the grid power demand of the equipment is distributed according to the power at each moment in each aggregation area and the cost of the aggregation area, and then taking the grid power demand distributed in each aggregation area as the balance constraint and the lowest power generation cost set by each aggregation area during the set period as the objective function, the grid power demand distributed in each aggregation area is redistributed.

[0009] Furthermore, the real-time operating power data of the device includes instantaneous power, average power, data for minimizing the fluctuation of the power load, start-stop constraint time of the power, and continuous operation constraint time of the power. Among them, the calculation formula for the data for minimizing the fluctuation of the power load is as follows:

[0010]

[0011] In the formula, f a is the optimization objective function of the device power, and the goal is to minimize the fluctuation of the power load during the operation of the device. C c is the power cost of production task c, ω c is the power usage of production task c within a certain time period, and Ω c is the additional penalty for power load fluctuation;

[0012] The calculation formula for the start-stop constraint time of the power is as follows:

[0013] t start = t c + T setup

[0014] t stop = t c + T end

[0015] In the formula, t start is the time when the device starts, t c is the production operation time of the device in a stable state, T setup is the adjustment time of the device from the initial state to the stable working state, t stop is the time when the device stops, and T end is the time of the device from the stable working state to the shutdown state;

[0016] The calculation formula for the continuous operation constraint time of the power is as follows:

[0017]

[0018] In the formula, γ c is the proportion of production task c in the device operation time; T c is the total operation time of production task c.

[0019] Furthermore, the calculation formula for the real-time carbon emission data of the device used in the production process based on the real-time operating power data of the device and the carbon emission factor is as follows:

[0020] E co2 = P total × EF × t

[0021] Wherein, E co2 is the carbon emission, P total is the total power load, EF is the carbon emission factor, and t is the fuel usage time;

[0022] Among them, the calculation formula of the total power load is shown as follows:

[0023] P total = P base + P var

[0024] Wherein, P total is the total power load, P base is the base power, and P var is the variable power.

[0025] Furthermore, taking the grid power demand of the device as the balance constraint and the minimum power generation cost set by the aggregator in a period as the objective function, the specific method for allocating the grid power demand of the device according to the power at each moment and the cost of each aggregation area is: calculating the total power capacity of each distributed source and load in the aggregation area through the grid power demand of the device, calculating the power generation cost of each aggregation area according to the total power capacity of each distributed source and load in the aggregation area, and taking the minimum power generation cost per hour as the objective function and the maximum and minimum output situations of the aggregation area as the constraint conditions to allocate the grid power demand of the device.

[0026] Furthermore, the calculation formula for calculating the total power capacity of each distributed source and load in the aggregation area through the grid power demand of the device is as follows:

[0027]

[0028] Wherein, represents the total output of the distributed photovoltaic power generation device at the t-th moment in the i-th aggregation area, represents the predicted output power of the i-th distributed photovoltaic power generation device at the t-th moment in the i-th aggregation area pv ;

[0029]

[0030] Wherein, represents the total output of the distributed wind power generation device at the t-th moment in the i-th aggregation area, represents the predicted output power of the i-th distributed wind power generation device at the t-th moment in the i-th aggregation area wp ;

[0031]

[0032] In the formula, represents the total output of the distributed traditional generator sets at the t-th moment in the i-th aggregation area, represents the rated output capacity of the ge th traditional generator set in the i-th aggregation area,

[0033]

[0034] In the formula, represents the total output of the distributed energy storage devices at the t-th moment in the i-th aggregation area, represents the maximum output capacity of the bat th distributed energy storage device in the i-th aggregation area,

[0035]

[0036] In the formula, represents the total output of the adjustable load devices at the t-th moment in the i-th aggregation area, represents the rated output capacity of the fleload th adjustable load in the i-th aggregation area,

[0037] The calculation formula for calculating the power generation cost of each aggregation area according to the total power capacity of each distributed source and load in the aggregation area is as follows:

[0038]

[0039] In the formula, is the power generation cost at the t-th moment in the i-th aggregation area, is the output cost of the distributed photovoltaic power generation device at the t-th moment, is the output cost of the distributed wind power generation device at the t-th moment, is the output cost of the traditional generator set at the t-th moment, is the output cost of the distributed energy storage device at the t-th moment, is the output cost of the adjustable load device at the t-th moment; represents the total output of the distributed photovoltaic power generation device at the t-th moment in the i-th aggregation area, represents the total output of the distributed wind power generation device at the t-th moment in the i-th aggregation area, represents the total output of the distributed traditional generator sets at the t-th moment in the i-th aggregation area, represents the total output of the distributed energy storage devices at the t-th moment in the i-th aggregation area, Denote the total output of the adjustable load devices in the $i$-th aggregation area at the $t$-th moment;

[0040] The calculation formula with the minimum hourly power generation cost as the objective function is:

[0041]

[0042] In the formula, $\min F$ t is the minimum power generation cost of the aggregator, is a decision variable, representing the allocated power value of the $i$-th aggregation area at the $t$-th moment, is the power generation cost of the $i$-th aggregation area at the $t$-th moment;

[0043] The calculation formulas for the maximum and minimum output conditions of the aggregation area as constraint conditions are shown as follows:

[0044]

[0045] In the formula, $P$ t i $\cdot\max$ represents the maximum output condition of the $i$-th aggregation area at the $t$-th moment, denotes the total output of the distributed photovoltaic power generation devices in the $i$-th aggregation area at the $t$-th moment, denotes the total output of the distributed wind power generation devices in the $i$-th aggregation area at the $t$-th moment, denotes the maximum power capacity of the total output of the conventional generator sets, denotes the total output of the distributed energy storage devices in the $i$-th aggregation area at the $t$-th moment, denotes the total output of the adjustable load devices in the $i$-th aggregation area at the $t$-th moment;

[0046]

[0047] In the formula, $P$ t i $\cdot\min$ represents the minimum output condition of the $i$-th aggregation area at the $t$-th moment, denotes the total output of the distributed photovoltaic power generation devices in the $i$-th aggregation area at the $t$-th moment, denotes the total output of the distributed wind power generation devices in the $i$-th aggregation area at the $t$-th moment, denotes the minimum power capacity of the total output of the conventional generator sets, denotes the total output of the distributed energy storage devices in the $i$-th aggregation area at the $t$-th moment, denotes the total output of the adjustable load devices in the $i$-th aggregation area at the $t$-th moment.

[0048] Furthermore, the calculation formula for the maximum power capacity of the total output of the conventional generator sets is:

[0049]

[0050] In the formula, represents the maximum power capacity of the total output of the conventional generator set, is the maximum output of the i-th conventional generator set at the t-th moment in the i-th aggregation area, ge for the i-th conventional generator set.

[0051] The calculation formula for the minimum power capacity of the total output of the conventional generator set is:

[0052]

[0053] In the formula, represents the minimum power capacity of the total output of the conventional generator set, is the minimum output of the i-th conventional generator set at the t-th moment in the i-th aggregation area,

[0054] The decision variables simultaneously satisfy the maximum and minimum value constraints and the supply-demand balance constraint. Among them, the calculation formula for the decision variables to satisfy the maximum and minimum value constraints is as follows:

[0055]

[0056] In the formula, is the decision variable, representing the power value allocated to the i-th aggregation area at the t-th moment, represents the maximum value of the decision variable, represents the minimum value of the decision variable;

[0057] Among them, the calculation formula for the decision variables to satisfy the supply-demand balance constraint is as follows:

[0058]

[0059] In the formula, is the decision variable, Demand-day t is the power allocated by the power grid to each distributed source load in the aggregation area at the t-th moment.

[0060] Furthermore, the calculation formula for the power grid power demand after allocation in each aggregation area as the balance constraint is as follows:

[0061]

[0062] In the formula, is the output situation of the i-th aggregation area at the t-th moment, is the output situation allocated to the i-th pv distributed photovoltaic power generation device in the i-th aggregation area at the t-th moment, is the output situation allocated to the i-th distributed photovoltaic power generation device at the t-th moment in the i-th aggregation area, pv and is the output situation allocated to the i-th traditional generator set device at the t-th moment in the i-th aggregation area, ge and is the output situation allocated to the i-th distributed energy storage device at the t-th moment in the i-th aggregation area, bat and is the output situation allocated to the i-th adjustable load at the t-th moment in the i-th aggregation area, fleload and

[0063] The calculation formula with the lowest power generation cost of the set period in each aggregation area as the objective function is:

[0064]

[0065] In the formula, minf t i represents the lowest power generation cost at the t-th moment in the i-th aggregation area, represents the decision variable of the i-th distributed photovoltaic power generation device at the t-th moment in the i-th aggregation area, pv and represents the decision variable of the i-th distributed wind power generation device at the t-th moment in the i-th aggregation area, wp and represents the decision variable of the i-th traditional generator set device at the t-th moment in the i-th aggregation area, ge and represents the decision variable of the i-th distributed energy storage device at the t-th moment in the i-th aggregation area, bat and represents the decision variable of the i-th adjustable load device at the t-th moment in the i-th aggregation area, fleload and is the output cost of the distributed photovoltaic power generation device at the t-th moment, is the output cost of the distributed wind power generation device at the t-th moment, is the output cost of the traditional generator set device at the t-th moment, is the output cost of the distributed energy storage device at the t-th moment, is the output cost of the adjustable load device at the t-th moment.

[0066] Furthermore, the output situation allocated to the i-th distributed photovoltaic power generation device at the t-th moment in the i-th aggregation area satisfies the following formula: pv and

[0067]

[0068] Wherein, is the output power allocated to the pv ith distributed photovoltaic power generation device at the tth moment in the ith aggregation area, represents the predicted output power of the pv ith distributed photovoltaic power generation device at the tth moment in the ith aggregation area, represents the variable of distributed photovoltaic power generation, with a value range of 0 to 1;

[0069] The output power allocated to the pv ith distributed wind power generation device at the tth moment in the ith aggregation area satisfies the following formula:

[0070]

[0071] Wherein, is the output power allocated to the pv ith distributed wind power generation device at the tth moment in the ith aggregation area, represents the predicted output power of the wp ith distributed wind power generation device at the tth moment in the ith aggregation area, represents the variable of distributed wind power generation, with a value range of 0 to 1;

[0072] The output power allocated to the fleload ith adjustable load at the tth moment in the ith aggregation area conforms to the maximum and minimum constraint conditions, and the maximum and minimum constraint conditions are shown in the following formula:

[0073]

[0074] Wherein, is the output power allocated to the fleload ith adjustable load at the tth moment in the ith aggregation area, represents the maximum output power of the adjustable load.

[0075] A multi-objective autonomous optimization regulation method for high-energy-consuming industrial loads designed in the second aspect of the present invention includes the following steps: obtaining energy consumption data of the production process and obtaining real-time operating power data of the equipment used in the production process; obtaining real-time carbon emission data of the equipment used in the production process according to the real-time operating power data of the equipment and the carbon emission factor; adjusting the production process to make the energy consumption data of the production process and the real-time carbon emission data of the equipment reach preset values, and obtaining the grid power demand of the equipment used in the adjusted production process; using the grid power demand of the equipment as a balance constraint and the lowest power generation cost set by the aggregator during a set period as the objective function, distributing the grid power demand of the equipment according to the power at each moment in each aggregation area and the cost of the aggregation area, and then using the grid power demand after distribution in each aggregation area as a balance constraint and the lowest power generation cost set by each aggregation area during the set period as the objective function to redistribute the grid power demand after distribution in each aggregation area.

[0076] Further, the real-time operating power data of the equipment includes instantaneous power, average power, data for minimizing the volatility of the power load, start-stop constraint time of the power, and continuous operation constraint time of the power. Among them, the calculation formula for the data for minimizing the volatility of the power load is:

[0077]

[0078] In the formula, f a is the optimization objective function of the equipment power, and the goal is to minimize the volatility of the power load during the operation of the equipment. C c is the power cost of the production and processing task c. ω c is the power usage of the production and processing task c within a certain time period. Ω c is the additional penalty when the power load fluctuates;

[0079] The calculation formula for the start-stop constraint time of the power is:

[0080] t start = t c + T setup

[0081] t stop = t c + T end

[0082] In the formula, t start is the time when the equipment starts. t c is the production operation time of the equipment in a stable state. T setup is the adjustment time of the equipment from the initial state to the stable working state. t stop is the time when the equipment stops. T end is the time of the equipment from the stable working state to the shutdown state;

[0083] The calculation formula for the continuous operation constraint time of the said power is as follows:

[0084]

[0085] In the formula, γ c is the proportion of production and processing task c in the equipment operation time; T c is the total operation time of production and processing task c.

[0086] Furthermore, the calculation formula for the real-time carbon emission data of the equipment used in the production process based on the real-time operation power data and carbon emission factor of the said equipment is as follows:

[0087] E co2 = P total × EF × t

[0088] In the formula, E co2 is the carbon emission, P total is the total power load, EF is the carbon emission factor, and t is the fuel usage time;

[0089] Among them, the calculation formula for the total power load is as follows:

[0090] P total = P base + P var

[0091] In the formula, P total is the total power load, P base is the base power, and P var is the variable power.

[0092] Furthermore, with the power demand of the said equipment for the power grid as the balance constraint and the minimum power generation cost set by the aggregator for a certain period as the objective function, the specific method for allocating the power demand of the said equipment for the power grid according to the power at each moment and the cost of each aggregation area is as follows: Calculate the total power capacity of each distributed source load in the aggregation area through the power demand of the said equipment for the power grid, calculate the power generation cost of each aggregation area according to the total power capacity of each distributed source load in the aggregation area, and take the minimum power generation cost per hour as the objective function and the maximum and minimum output situations of the aggregation area as the constraint conditions to allocate the power demand of the said equipment for the power grid.

[0093] Furthermore, the calculation formula for calculating the total power capacity of each distributed source load in the aggregation area through the power demand of the said equipment for the power grid is as follows:

[0094]

[0095] In the formula, Denotes the total output of distributed photovoltaic power generation equipment at the $t$-th moment in the $i$-th aggregation area, Denotes the predicted output power of the $i$-th pv distributed photovoltaic power generation equipment at the $t$-th moment in the $i$-th aggregation area,

[0096]

[0097] In the formula, Denotes the total output of distributed wind power generation equipment at the $t$-th moment in the $i$-th aggregation area, Denotes the predicted output power of the $i$-th wp distributed wind power generation equipment at the $t$-th moment in the $i$-th aggregation area,

[0098]

[0099] In the formula, Denotes the total output of distributed traditional generator set equipment at the $t$-th moment in the $i$-th aggregation area, Denotes the rated output capacity of the $i$-th ge traditional generator set equipment in the $i$-th aggregation area,

[0100]

[0101] In the formula, Denotes the total output of distributed energy storage equipment at the $t$-th moment in the $i$-th aggregation area, Denotes the maximum output capacity of the $i$-th bat distributed energy storage equipment in the $i$-th aggregation area,

[0102]

[0103] In the formula, Denotes the total output of adjustable load equipment at the $t$-th moment in the $i$-th aggregation area, Denotes the rated output capacity of the $i$-th fleload adjustable load in the $i$-th aggregation area,

[0104] The calculation formula for calculating the power generation cost of each aggregation area according to the total power capacity of each distributed source and load in the aggregation area is as follows:

[0105]

[0106] In the formula, Is the power generation cost at the $t$-th moment in the $i$-th aggregation area, is the output cost of the distributed photovoltaic power generation equipment at the t-th moment, is the output cost of the distributed wind power generation equipment at the t-th moment, is the output cost of the traditional generator set equipment at the t-th moment, is the output cost of the distributed energy storage equipment at the t-th moment, is the output cost of the adjustable load equipment at the t-th moment; represents the total output of the distributed photovoltaic power generation equipment in the i-th aggregation area at the t-th moment, represents the total output of the distributed wind power generation equipment in the i-th aggregation area at the t-th moment, represents the total output of the distributed traditional generator set equipment in the i-th aggregation area at the t-th moment, represents the total output of the distributed energy storage equipment in the i-th aggregation area at the t-th moment, represents the total output of the adjustable load equipment in the i-th aggregation area at the t-th moment;

[0107] The calculation formula with the minimum hourly power generation cost as the objective function is:

[0108]

[0109] In the formula, min F t is the minimum power generation cost of the aggregator, is the decision variable, representing the allocated power value of the aggregation area i at the t-th moment, is the power generation cost of the i-th aggregation area at the t-th moment;

[0110] The calculation formula with the maximum and minimum output conditions of the aggregation area as the constraint conditions is shown as follows:

[0111]

[0112] In the formula, P t i ·max represents the maximum output condition of the aggregation area i at the t-th moment, represents the total output of the distributed photovoltaic power generation equipment in the i-th aggregation area at the t-th moment, represents the total output of the distributed wind power generation equipment in the i-th aggregation area at the t-th moment, represents the maximum power capacity of the total output of the conventional generator set, represents the total output of the distributed energy storage equipment in the i-th aggregation area at the t-th moment, represents the total output of the adjustable load equipment in the i-th aggregation area at the t-th moment;

[0113]

[0114] In the formula, Pt i ·min represents the minimum output of the aggregation area i at time t. represents the total output of the distributed photovoltaic power generation equipment in the i-th aggregation area at time t. represents the total output of the distributed wind power generation equipment in the i-th aggregation area at time t. represents the minimum power capacity of the total output of the conventional generator sets. represents the total output of the distributed energy storage equipment in the i-th aggregation area at time t. represents the total output of the adjustable load equipment in the i-th aggregation area at time t.

[0115] Furthermore, the calculation formula for the maximum power capacity of the total output of the conventional generator sets is:

[0116]

[0117] In the formula, represents the maximum power capacity of the total output of the conventional generator sets. is the maximum output of the i-th conventional generator set at time t in the i-th aggregation area. ge for the i-th conventional generator set.

[0118] The calculation formula for the minimum power capacity of the total output of the conventional generator sets is:

[0119]

[0120] In the formula, represents the minimum power capacity of the total output of the conventional generator sets. is the minimum output of the i-th conventional generator set at time t in the i-th aggregation area. ge for the i-th conventional generator set.

[0121] The decision variables simultaneously satisfy the maximum and minimum value constraints and the supply-demand balance constraint. Among them, the calculation formula for the decision variables to satisfy the maximum and minimum value constraints is as follows:

[0122]

[0123] In the formula, is the decision variable, representing the allocated power value of the aggregation area i at time t. represents the maximum value of the decision variable. represents the minimum value of the decision variable.

[0124] Among them, the calculation formula for the decision variables to satisfy the supply-demand balance constraint is as follows:

[0125]

[0126] In the formula, is a decision variable, Demand-day t is the power allocated by the power grid to each distributed source and load in the aggregation area at time t.

[0127] Furthermore, the calculation formula for the balance constraint with the power demand of the power grid after allocation in each aggregation area is as follows:

[0128]

[0129] In the formula, is the output situation of the i-th aggregation area at time t, is the output situation allocated to the i-th pv distributed photovoltaic power generation equipment in the i-th aggregation area at time t, is the output situation allocated to the i-th pv distributed wind power generation equipment in the i-th aggregation area at time t, is the output situation allocated to the i-th ge conventional generator set equipment in the i-th aggregation area at time t, is the output situation allocated to the i-th bat distributed energy storage equipment in the i-th aggregation area at time t, is the output situation allocated to the i-th fleload adjustable load in the i-th aggregation area at time t,

[0130] The calculation formula for the objective function with the lowest power generation cost during the set period in each aggregation area is:

[0131]

[0132] In the formula, minf t i represents the lowest power generation cost of the i-th aggregation area at time t, represents the decision variable of the i-th pv distributed photovoltaic power generation equipment in the i-th aggregation area at time t, represents the decision variable of the i-th wp distributed wind power generation equipment in the i-th aggregation area at time t, represents the decision variable of the i-th ge conventional generator set equipment in the i-th aggregation area at time t, represents the decision variable of the i-th bat distributed energy storage equipment in the i-th aggregation area at time t, The decision variable representing the i-th adjustable load device at the t-th moment in the i-th aggregation area fleload for the i-th adjustable load device is the output cost of the distributed photovoltaic power generation device at the t-th moment is the output cost of the distributed wind power generation device at the t-th moment is the output cost of the traditional generator set device at the t-th moment is the output cost of the distributed energy storage device at the t-th moment is the output cost of the adjustable load device at the t-th moment

[0133] Furthermore, the output situation allocated to the i-th distributed photovoltaic power generation device at the t-th moment in the i-th aggregation area satisfies the following formula: pv for the i-th distributed photovoltaic power generation device

[0134]

[0135] In the formula, is the output situation allocated to the i-th distributed photovoltaic power generation device at the t-th moment in the i-th aggregation area pv for the i-th distributed photovoltaic power generation device represents the predicted output power of the i-th distributed photovoltaic power generation device at the t-th moment in the i-th aggregation area pv for the i-th distributed photovoltaic power generation device represents the variable of distributed photovoltaic power generation, with a value range of 0 to 1;

[0136] The output situation allocated to the i-th distributed wind power generation device at the t-th moment in the i-th aggregation area satisfies the following formula: pv for the i-th distributed wind power generation device

[0137]

[0138] In the formula, is the output situation allocated to the i-th distributed wind power generation device at the t-th moment in the i-th aggregation area pv for the i-th distributed wind power generation device represents the predicted output power of the i-th distributed wind power generation device at the t-th moment in the i-th aggregation area wp for the i-th distributed wind power generation device represents the variable of distributed wind power generation, with a value range of 0 to 1;

[0139] The output situation allocated to the i-th adjustable load at the t-th moment in the i-th aggregation area conforms to the maximum and minimum constraint conditions, and the maximum and minimum constraint conditions are shown in the following formula: fleload for the i-th adjustable load

[0140]

[0141] In the formula, is the output situation of the i-th adjustable load allocated at the t-th moment in the i-th aggregation area, fleload where represents the maximum output of the adjustable load.

[0142] A computer-readable storage medium designed in the third aspect of the present invention, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the steps of the method described above.

[0143] Advantages of the present invention:

[0144] (1) The load characteristic extraction method based on data and model-driven can accurately predict electricity demand and adjust equipment power in real time by deeply mining and analyzing the electricity consumption data of industrial users and precisely extracting and clustering load characteristics. This intelligent load management not only helps optimize the electricity consumption period and power, but also significantly improves the response speed and flexibility of the power grid in application scenarios such as day-ahead and intra-day demand response and power ancillary service markets. Through precise regulation, it promotes the efficient consumption of renewable energy and greatly enhances the adaptability of the power grid to new energy sources such as distributed photovoltaics;

[0145] (2) By adopting this load characteristic extraction method, high-energy-consuming industrial users can achieve refined management at the internal equipment level. This method helps users identify peak energy consumption and optimize equipment operation strategies by real-time analyzing equipment operation data, thereby significantly improving energy utilization efficiency and reducing energy consumption costs. For market-oriented users, participating in the power demand response and ancillary service markets, through precise load characteristic extraction, they can obtain corresponding market incentives, further reducing production costs and enhancing enterprise competitiveness;

[0146] (3) By optimizing the power resource allocation, promoting load transfer and peak shaving and valley filling through the load characteristic extraction of high-energy-consuming industrial users, this method improves energy utilization efficiency, reduces carbon emissions and pollution. It supports the access of renewable energy, promotes the development of the green power market, enhances the flexibility and reliability of the power grid, and helps achieve sustainable development goals. Using the data provided by advanced metering infrastructure, this method promotes the smart grid and digital transformation, optimizes industrial electricity consumption behavior, and enhances users' environmental awareness and social responsibility, overall promoting the use of green energy and environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0147] Figure 1 is a structural block diagram of a multi-objective autonomous optimization regulation system for high-energy-consuming industrial loads according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0148] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments:

[0149] Example 1

[0150] A multi-objective autonomous optimization and regulation system for high-energy-consuming industrial loads, as Figure 1 shown, which includes an energy consumption and operation parameter acquisition module, a carbon emission analysis module, and a two-layer optimization scheduling module; the energy consumption and operation parameter acquisition module is used to acquire the energy consumption data of the production process and the real-time operating power data of the equipment used in the production process; the carbon emission analysis module obtains the real-time carbon emission data of the equipment used in the production process according to the real-time operating power data of the equipment and the carbon emission factor; the two-layer optimization scheduling module adjusts the production process to make the energy consumption data of the production process and the real-time carbon emission data of the equipment reach preset values, and obtains the grid power demand of the equipment used in the adjusted production process; taking the grid power demand of the equipment as the balance constraint and the lowest power generation cost set by the aggregator during the set period as the objective function, the grid power demand of the equipment is allocated according to the power at each moment in each aggregation area and the cost of the aggregation area, and then taking the grid power demand allocated to each aggregation area as the balance constraint and the lowest power generation cost set by each aggregation area during the set period as the objective function, the grid power demand allocated to each aggregation area is allocated again.

[0151] In this article, the production process of high-energy-consuming industries clarifies the technological processes of each production link, which guides the direction for the real-time carbon emission data of the equipment. According to the characteristics of energy demand in different processes, the carbon emission analysis module can specifically analyze the carbon emission situation of the equipment in each process stage. For example, in the high-temperature forging process, due to high energy consumption, combined with the power data of the operation characteristic model, the carbon emission of the equipment in this link is monitored key, providing a basis for subsequent process improvement and equipment upgrade to achieve carbon emission reduction from the process level. At the same time, the energy consumption mode analyzed by the energy consumption and operation parameter acquisition module is closely combined with the carbon emission analysis module. Knowing the energy consumption elasticity of each process step, it is possible to combine the carbon emission characteristics to judge which processes can effectively reduce emissions while saving energy, and which processes need to balance production and carbon emissions. For processes with low energy consumption but high carbon emissions, priority is given to process adjustment or equipment replacement to ensure that the energy use and carbon emissions throughout the production process are within a reasonable control range.

[0152] In the above technical solution, the real-time operating power data of the equipment includes instantaneous power, average power, data for minimizing the volatility of the power load, the start-stop constraint time of the power, and the continuous operation constraint time of the power. Among them, the calculation formula for the instantaneous power is shown as follows:

[0153] P(t) = V(t)·I(t)·cos(Φ(t))

[0154] Wherein, P(t) represents the instantaneous power in watts (W); V(t) represents the instantaneous voltage in volts (V); I(t) represents the instantaneous current in amperes (A); Φ(t) represents the phase difference between the voltage and the current, indicating the power factor. In the iron and steel industry, the instantaneous power is used to monitor the instantaneous power of blast furnaces or electric arc furnaces in real time, capturing the electricity demand during equipment startup, shutdown, and full-load operation; in the cement industry, the fluctuations in the instantaneous power of rotary kilns and grinding equipment can reveal their operating status, helping to identify abnormal power fluctuations; in the aluminum electrolysis industry, the instantaneous power is used to monitor the instantaneous power output of electrolytic cells in real time, especially when adjusting the current of electrolytic cells, capturing the instantaneous changes in energy consumption.

[0155] In this article, the calculation formula for the average power is shown as follows:

[0156]

[0157] Wherein, P avg represents the average power; T represents the length of the time period in seconds (s); P(t) is the instantaneous power of the production equipment. In the iron and steel industry, during long-term monitoring, it is used to measure the average power of electric arc furnaces or rolling mills, optimizing the equipment operation strategy and reducing unnecessary energy consumption fluctuations; in the cement industry, evaluating the long-term average power consumption of rotary kilns and vertical mills helps to adjust the equipment load and improve the overall energy efficiency; in the aluminum electrolysis industry, analyzing the long-term operating power of rectifying equipment and electrolytic cells ensures stable current load and reduces unnecessary power losses.

[0158] For continuous production equipment in the iron and steel, cement, and aluminum electrolysis industries, such as blast furnaces and converters in iron and steel, rotary kilns in cement, and electrolytic cells in aluminum electrolysis, the operating power of these equipment must remain stable throughout the production cycle. Power fluctuations not only affect the normal operation of the equipment but may also lead to a decrease in production efficiency and even damage to the equipment. Therefore, minimizing the volatility of the power load becomes a key optimization goal. Thus, the calculation formula for the data of minimizing the volatility of the power load is:

[0159]

[0160] Wherein, f a is the optimization objective function of the equipment power, aiming to minimize the volatility of the power load during the equipment operation, C c is the power cost of the production processing task c (production processing and manufacturing tasks, etc.), ω c is the power consumption of the production processing task c within a certain time period, Ω c is the additional penalty when the power load fluctuates (the additional penalty refers to not meeting the grid security and stability operation or power market reporting and quoting constraints, etc.).

[0161] The start-stop behavior of the equipment power is particularly crucial in the steel industry, especially for high-energy-consuming equipment such as blast furnaces and converters. A large amount of energy is consumed during their startup and shutdown processes, so reasonable control must be carried out. Therefore, the calculation formula for the start-stop constraint time of the power is:

[0162] t start =t c +T setup

[0163] t stop =t c +T end

[0164] In the formula, t start is the time when the equipment starts up, t c is the production operation time in the stable state of the equipment (i.e., the normal working state), T setup is the adjustment time for the equipment to go from the initial state S setup to the stable working state S steady ; t stop is the time when the equipment stops, and T end is the time for the equipment to go from the stable working state S steady to the shutdown state S end .

[0165] The running time of the equipment within a production cycle is crucial. The power must remain relatively stable during the running time of the equipment and gradually decrease to the base load after the production task is completed. Therefore, the calculation formula for the continuous operation constraint time of the power is:

[0166]

[0167] In the formula, γ c is the proportion of the production and processing task c in the running time of the equipment; T c is the total running time of the production and processing task c.

[0168] In the above technical solution, the real-time operating power data of the equipment also includes the cumulative energy consumption of the equipment. The cumulative energy consumption is used to calculate the total energy consumption of the equipment within a certain period of time and is calculated by integrating the power over time. The formula is as follows:

[0169]

[0170] In the formula, E(t) represents the cumulative energy consumption, with the unit of joule (J) or kilowatt-hour (kWh); P(t) represents the instantaneous power, with the unit of watt (W); t represents the time variable, with the unit of second (s).

[0171] In the actual operation of the equipment, energy consumption often needs to be calculated in stages. Therefore, the cumulative energy consumption can be extended to piecewise integration, and the formula is as follows:

[0172]

[0173] In the formula, E(t) represents the cumulative energy consumption, with the unit of joule (J) or kilowatt-hour (kWh); P(t) represents the instantaneous power, with the unit of watt (W); t represents the time variable, with the unit of second (s); n is the number of time periods; t i is the demarcation point of each time period. In the iron and steel industry, the total energy consumption of blast furnaces and continuous casters is accumulated to evaluate the energy consumption of each process during the smelting process; in the cement industry, the cumulative energy consumption of each stage during the continuous operation of ball mills and grinding equipment is calculated to optimize the equipment production scheduling and operation rhythm; in the electrolytic aluminum industry, the cumulative energy consumption is used to calculate the total energy consumption of electrolytic cells during long-term operation to help improve the power dispatching strategy.

[0174] The real-time operating power data of the equipment obtained by the energy consumption and operating parameter acquisition module provides basic data support for the double-layer optimal scheduling module. Through the real-time operating power data of the equipment, the double-layer optimal scheduling module can accurately grasp the energy consumption demand and change trend of the equipment, reasonably arrange the start-stop sequence and operation time period of the equipment, so as to realize the optimal distribution of the overall power and achieve the purpose of energy conservation, loss reduction and efficiency improvement. For example, when the energy consumption and operating parameter acquisition module monitors that the power of a certain key equipment fluctuates violently during a specific period, the double-layer optimal scheduling module can adjust the operation plan of other associated equipment in advance to avoid power surges, ensure the stable operation of the system, and at the same time accurately calculate the total power capacity required according to the power demand.

[0175] For the production equipment in high-energy-consuming industries such as iron and steel, cement, and electrolytic aluminum, it is crucial to analyze their power characteristics and carbon emission characteristics. These industries consume a large amount of energy during the production process, resulting in a relatively high carbon emission level. The real-time operating power data of the equipment provided by the energy consumption and operating parameter acquisition module is the basis for the carbon emission analysis module; the instantaneous power, average power, and the curve of power change over time obtained by the energy consumption and operating parameter acquisition module are the key inputs for calculating carbon emissions. For example, by multiplying the instantaneous power by the unit time and combining the known carbon emission factor per unit power, the carbon emissions of the equipment at each moment can be accurately calculated, providing real-time and accurate data support for carbon emission calculation. The carbon emission data calculated by the carbon emission analysis module, in turn, can provide a new perspective for the energy consumption and operating parameter acquisition module. When it is found that the carbon emissions of a certain equipment increase abnormally during a specific period, the energy consumption and operating parameter acquisition module can trace back and check the power fluctuations, operating stability, etc. of the equipment during this period to determine whether there are factors such as equipment failures and abnormal operating conditions leading to unreasonable power utilization and thus out-of-control carbon emissions, realizing the dynamic collaborative analysis of the two sets of data.

[0176] In the above technical solution, the calculation formula for the real-time carbon emission data of the equipment used in the production process based on the real-time operating power data and carbon emission factors of the equipment is as follows:

[0177] E co2 =P total ×EF×t

[0178] In the formula, E co2 is the carbon emission, with the unit of ton, P total is the total power load, EF is the carbon emission factor, and t is the fuel usage time; among them, the carbon emission factor is usually determined according to the fuel type and usage efficiency of the equipment. Specifically, the fuel type is one of the core factors affecting the carbon emission factor. Different fuels will produce different amounts of greenhouse gases during combustion or use. For example, the combustion of fossil fuels such as coal, oil, and natural gas will produce a large amount of carbon dioxide, while biomass fuels may produce relatively low carbon emissions under certain conditions. Therefore, the fuel type is crucial for accurately calculating the carbon emission factor. Secondly, the usage efficiency of the equipment is also an important factor affecting the carbon emission factor. High-efficiency equipment requires less fuel for the same output, so the greenhouse gas emissions generated are also correspondingly reduced. On the contrary, low-efficiency equipment may require more fuel to achieve the same output, resulting in higher greenhouse gas emissions. Therefore, the energy efficiency level of the equipment also has an important impact on the determination of the carbon emission factor, with the unit of ton CO2 / MWh.

[0179] In the above technical solution, the calculation formula for the total power load is as follows:

[0180] P total =P base +P var

[0181] In the formula, P total is the total power load (a function of time), with the unit of kW; P base is the base power, that is, the fixed power load of the equipment in the no-load state (the power of the equipment when it is idling); P var is the variable power, which varies with different production conditions.

[0182] In this article, the steel industry is one of the main sources of energy consumption and carbon emissions. The main production equipment includes blast furnaces, converters, electric furnaces, etc. Among them, the carbon emissions of blast furnaces mainly come from the combustion process of fuels such as coal and coke, and its carbon emission characteristics can be estimated by the following formula:

[0183]

[0184] In the formula, E CO2-HFis the total carbon emissions of the blast furnace; M coal , M coke are the masses of coal and coke respectively; H eff is the fuel utilization efficiency of the blast furnace; R recovery is the waste heat recovery coefficient; F CO2-coke , F CO2-coal are the carbon emission factors of coke and coal respectively; η heat is the thermal efficiency of the blast furnace. This formula calculates the total carbon emissions of the blast furnace when using coal and coke, taking into account waste heat recovery and fuel utilization efficiency, and can effectively evaluate the environmental impact of the blast furnace. The carbon emission factors of coal and coke reflect the environmental burden of the fuel.

[0185] An electric arc furnace uses electricity for steel production, and its carbon emissions mainly come from electricity consumption and a small amount of electrode loss. The carbon emission model of the electric arc furnace is:

[0186]

[0187] In the formula, E CO2-EAF is the total carbon emissions of the electric arc furnace; P elec is the electric power of the electric arc furnace; t run is the working time of the electric arc furnace; F elec is the carbon emission coefficient of electricity; M electrode is the mass of the consumed electrode material; η electrode is the electrode consumption frequency; F CO2-electrode is the carbon emission factor of electrode consumption. This formula reflects the carbon emission characteristics of the electric arc furnace under the consumption of electric energy and electrode materials, facilitating the analysis of the impact of the power source on emissions. The consumption efficiency of the electrode and its carbon emission factor enable enterprises to evaluate the optimization plan for electrode use.

[0188] A converter is a key device for converting pig iron into steel, and its carbon emissions mainly come from the reaction process of fuel and hot metal. The carbon emission model of the converter is:

[0189] E CO2-BOF =(M scrap ×F CO2-scrap +P fuel ×F CO2-fuel )×t toperation

[0190] In the formula, E CO2-BOF is the total carbon emissions of the converter, in tons / CO2; M scrap is the mass of scrap steel, in tons; F CO2-scrap is the carbon emission factor of scrap steel; F CO2-fuel is the carbon emission factor of the fuel; P fuel is the fuel power used by the converter; t toperationis the operation time of the converter. This formula comprehensively considers the carbon emissions of scrap steel and fuel and is applicable to evaluating the carbon emission characteristics of the converter under different production conditions.

[0191] The carbon emission analysis module inputs the carbon emission data of high-energy-consuming industries into the two-layer optimal scheduling module, which becomes one of the important constraint conditions of the optimization objective function. When the scheduling module arranges equipment scheduling, it not only considers power balance and production efficiency but also takes into account the minimization of carbon emissions, prompting high-energy-consuming enterprises to develop towards the direction of green and low-carbon while meeting production requirements. For example, when formulating a scheduling plan, priority is given to arranging the operation of equipment with low carbon emissions, and load reduction or peak-shifting operation adjustment is carried out for high-carbon-emission equipment.

[0192] In the above technical solution, the specific method for adjusting the production process to make the energy consumption data of the production process and the real-time carbon emission data of the equipment reach the preset value is as follows: considering power balance and production efficiency, and also taking into account the minimization of carbon emissions, prompting high-energy-consuming enterprises to develop towards the direction of green and low-carbon while meeting production requirements.

[0193] In this article, after the upper-layer central controller in the two-layer optimal scheduling module receives the work instruction sent by the power grid hourly, taking the power grid power demand of the equipment as the balance constraint and the minimum hourly power generation cost as the objective function, it distributes the power grid power demand of the equipment according to the power at each moment and the cost of each aggregation area of each aggregation area.

[0194] In the above technical solution, the specific method for distributing the power grid power demand of the equipment according to the power at each moment and the cost of each aggregation area with the power grid power demand of the equipment as the balance constraint and the minimum power generation cost set by the aggregator during a period as the objective function is as follows: calculating the total power capacity of each distributed source load in the aggregation area through the power grid power demand of the equipment, calculating the power generation cost of each aggregation area according to the total power capacity of each distributed source load in the aggregation area, taking the minimum hourly power generation cost as the objective function, and taking the maximum and minimum output situations of the aggregation area as the constraint conditions to distribute the power grid power demand of the equipment.

[0195] In the above technical solution, the calculation formula for calculating the total power capacity of each distributed source load in the aggregation area through the power grid power demand of the equipment is as follows:

[0196]

[0197] In the formula, represents the total output of the distributed photovoltaic power generation equipment at the t-th moment in the i-th aggregation area, represents the predicted output power of the pv i-th distributed photovoltaic power generation equipment at the t-th moment in the i-th aggregation area,

[0198]

[0199] In the formula, represents the total output of the distributed wind power generation equipment at the t-th moment in the i-th aggregation area, represents the predicted output power of the wp i-th distributed wind power generation equipment at the t-th moment in the i-th aggregation area,

[0200]

[0201] In the formula, represents the total output of the distributed traditional generator set equipment at the t-th moment in the i-th aggregation area, represents the ge rated output capacity of the i-th traditional generator set equipment in the i-th aggregation area,

[0202]

[0203] In the formula, represents the total output of the distributed energy storage equipment at the t-th moment in the i-th aggregation area, represents the bat maximum output capacity of the i-th distributed energy storage equipment in the i-th aggregation area,

[0204]

[0205] In the formula, represents the total output of the adjustable load equipment at the t-th moment in the i-th aggregation area, represents the fleload rated output capacity of the i-th adjustable load in the i-th aggregation area,

[0206] In the above technical solution, the calculation formula for the power generation cost of each aggregation area according to the total power capacity of each distributed source and load in the aggregation area is as follows:

[0207]

[0208] In the formula, is the power generation cost at the t-th moment in the i-th aggregation area, is the output cost of the distributed photovoltaic power generation equipment at the t-th moment, is the output cost of the distributed wind power generation equipment at the t-th moment, is the output cost of the traditional generator set equipment at the t-th moment, is the output cost of the distributed energy storage device at the t-th moment, is the output cost of the adjustable load device at the t-th moment, represents the total output of the distributed photovoltaic power generation device in the i-th aggregation area at the t-th moment, represents the total output of the distributed wind power generation device in the i-th aggregation area at the t-th moment, represents the total output of the distributed traditional generator set device in the i-th aggregation area at the t-th moment, represents the total output of the distributed energy storage device in the i-th aggregation area at the t-th moment, represents the total output of the adjustable load device in the i-th aggregation area at the t-th moment.

[0209] In the above technical solution, the calculation formula with the minimum hourly power generation cost as the objective function is:

[0210]

[0211] In the formula, min F t is the minimum power generation cost of the aggregator, is the decision variable, representing the allocated power value of the i-th aggregation area at the t-th moment, is the power generation cost of the i-th aggregation area at the t-th moment;

[0212] The calculation formula for the maximum and minimum output conditions of the aggregation area as constraints is shown as follows:

[0213]

[0214] In the formula, P t i ·max represents the maximum output condition of the i-th aggregation area at the t-th moment, represents the total output of the distributed photovoltaic power generation device in the i-th aggregation area at the t-th moment, represents the total output of the distributed wind power generation device in the i-th aggregation area at the t-th moment, represents the maximum power capacity of the total output of the conventional generator set, represents the total output of the distributed energy storage device in the i-th aggregation area at the t-th moment, represents the total output of the adjustable load device in the i-th aggregation area at the t-th moment;

[0215]

[0216] In the formula, P t i ·min represents the minimum output condition of the i-th aggregation area at the t-th moment, represents the total output of the distributed photovoltaic power generation device in the i-th aggregation area at the t-th moment, represents the total output of distributed wind power generation equipment at the t-th moment in the i-th aggregation area, represents the minimum power capacity of the total output of conventional generating units, represents the total output of distributed energy storage equipment at the t-th moment in the i-th aggregation area, represents the total output of adjustable load equipment at the t-th moment in the i-th aggregation area.

[0217] In the above technical solution, the calculation formula for the maximum power capacity of the total output of conventional generating units is:

[0218]

[0219] In the formula, represents the maximum power capacity of the total output of conventional generating units, is the maximum output of the i-th conventional generating unit at the t-th moment in the i-th aggregation area, ge

[0220] The calculation formula for the minimum power capacity of the total output of conventional generating units is:

[0221]

[0222] In the formula, represents the minimum power capacity of the total output of conventional generating units, is the minimum output of the i-th conventional generating unit at the t-th moment in the i-th aggregation area, ge

[0223] The decision variables simultaneously satisfy the maximum and minimum value constraints and the supply-demand balance constraint. Among them, the calculation formula for the decision variables to satisfy the maximum and minimum value constraints is as follows:

[0224]

[0225] In the formula, is the decision variable, representing the allocated power value of aggregation area i at the t-th moment, represents the maximum value of the decision variable, represents the minimum value of the decision variable;

[0226] Among them, the calculation formula for the decision variables to satisfy the supply-demand balance constraint is as follows:

[0227]

[0228] In the formula, is the decision variable, and Demand-dayt is the power allocated by the power grid to each distributed source load in the aggregation area at the t-th moment. ​​

[0229] In this article, after receiving the hourly work instructions from the upper-layer central controller, the centralized controller of the lower layer in the double-layer optimal scheduling module redistributes the power demand of the power grid allocated to each aggregation area, taking into account the working characteristics and generation costs of various distributed resources in the aggregation area, with the power demand of the power grid allocated to each aggregation area as the balance constraint and the minimum generation cost of the set time period in each aggregation area as the objective function.

[0230] In the above technical solution, the calculation formula with the power demand of the power grid allocated to each aggregation area as the balance constraint is as follows:

[0231]

[0232] In the formula, is the output situation of the i-th aggregation area at the t-th moment, is the allocated output situation of the i-th distributed photovoltaic power generation device in the i-th aggregation area at the t-th moment, pv is the allocated output situation of the i-th distributed wind power generation device in the i-th aggregation area at the t-th moment, is the allocated output situation of the i-th traditional generator set device in the i-th aggregation area at the t-th moment, pv is the allocated output situation of the i-th distributed energy storage device in the i-th aggregation area at the t-th moment, is the allocated output situation of the i-th adjustable load in the i-th aggregation area at the t-th moment, ge is the allocated output situation of the i-th distributed energy storage device in the i-th aggregation area at the t-th moment, is the allocated output situation of the i-th adjustable load in the i-th aggregation area at the t-th moment, bat is the allocated output situation of the i-th distributed energy storage device in the i-th aggregation area at the t-th moment, is the allocated output situation of the i-th adjustable load in the i-th aggregation area at the t-th moment, fleload is the allocated output situation of the i-th adjustable load in the i-th aggregation area at the t-th moment,

[0233] In the above technical solution, the calculation formula with the minimum generation cost of the set time period in each aggregation area as the objective function is:

[0234]

[0235] In the formula, minf t i represents the minimum generation cost of the i-th aggregation area at the t-th moment, represents the decision variable of the i-th distributed photovoltaic power generation device in the i-th aggregation area at the t-th moment, pv represents the decision variable of the i-th distributed wind power generation device in the i-th aggregation area at the t-th moment, represents the decision variable of the i-th distributed wind power generation device in the i-th aggregation area at the t-th moment, wp represents the decision variable of the i-th distributed wind power generation device in the i-th aggregation area at the t-th moment, represents the decision variable of the i-th traditional generator set device in the i-th aggregation area at the t-th moment, geDecision variables of a traditional generator set device represents the decision variable of the bat ith distributed energy storage device at the tth moment in the ith aggregation area represents the decision variable of the fleload ith adjustable load device at the tth moment in the ith aggregation area is the output cost of the distributed photovoltaic power generation device at the tth moment is the output cost of the distributed wind power generation device at the tth moment is the output cost of the traditional generator set device at the tth moment is the output cost of the distributed energy storage device at the tth moment is the output cost of the adjustable load device at the tth moment

[0236] In the above technical solution, since distributed photovoltaics and distributed wind power are non-dispatchable power sources, their output conditions can be defined according to the distributed energy constraints. Specifically, the output condition assigned to the pv ith distributed photovoltaic power generation device at the tth moment in the ith aggregation area satisfies the following formula:

[0237]

[0238] In the formula, is the output condition assigned to the pv ith distributed photovoltaic power generation device at the tth moment in the ith aggregation area represents the predicted output power of the pv ith distributed photovoltaic power generation device at the tth moment in the ith aggregation area represents the variable of distributed photovoltaic power generation, with a value range of 0 to 1, indicating whether the distributed resource operates according to the predicted power at this moment;

[0239] The output condition assigned to the pv ith distributed wind power generation device at the tth moment in the ith aggregation area satisfies the following formula:

[0240]

[0241] In the formula, is the output condition assigned to the pv ith distributed wind power generation device at the tth moment in the ith aggregation area represents the predicted output power of the wp ith distributed wind power generation device at the tth moment in the ith aggregation area represents the variable of distributed wind power generation, with a value range of 0 to 1, indicating whether the distributed resource operates according to the predicted power at this moment.

[0242] In the above technical solution, the conventional generator set, distributed energy storage, and flexible load are dispatchable power sources. Among them, the constraint conditions of the conventional generator set and distributed energy storage are the same as those of the upper-layer dispatching model, and the output of the flexible load conforms to the minimum and maximum value constraints. Specifically, the output of the i-th adjustable load at the t-th moment in the i-th aggregation area conforms to the minimum and maximum value constraint conditions, and the minimum and maximum value constraint conditions are shown in the following formula: fleload The output of the i-th adjustable load at the t-th moment in the i-th aggregation area conforms to the minimum and maximum value constraint conditions, and the minimum and maximum value constraint conditions are as follows:

[0243]

[0244] In the formula, is the output of the i-th adjustable load at the t-th moment in the i-th aggregation area, fleload and represents the maximum output of the adjustable load.

[0245] Embodiment 2

[0246] A multi-objective autonomous optimization regulation method for high-energy-consuming industrial loads, which includes the following: obtaining the energy consumption data of the production process and obtaining the real-time operating power data of the equipment used in the production process; obtaining the real-time carbon emission data of the equipment used in the production process according to the real-time operating power data of the equipment and the carbon emission factor; adjusting the production process to make the energy consumption data of the production process and the real-time carbon emission data of the equipment reach the preset values, and obtaining the grid power demand of the equipment used in the adjusted production process; using the grid power demand of the equipment as the balance constraint and the lowest power generation cost set by the aggregator during the set period as the objective function, distributing the grid power demand of the equipment according to the power at each moment of each aggregation area and the cost of the aggregation area, and then using the grid power demand distributed to each aggregation area as the balance constraint and the lowest power generation cost set by each aggregation area during the set period as the objective function, and redistributing the grid power demand distributed to each aggregation area.

[0247] In the above technical solution, the real-time operating power data of the equipment includes instantaneous power, average power, data for minimizing the volatility of the power load, start-stop constraint time of the power, and continuous operation constraint time of the power. Among them, the calculation formula of the instantaneous power is shown in the following formula:

[0248] P(t) = V(t)·I(t)·cos(Φ(t))

[0249] Wherein, P(t) represents the instantaneous power, with the unit of watt (W); V(t) represents the instantaneous voltage, with the unit of volt (V); I(t) represents the instantaneous current, with the unit of ampere (A); Φ(t) represents the phase difference between the voltage and the current, indicating the power factor. In the iron and steel industry, the instantaneous power is used to monitor the instantaneous power of blast furnaces or electric arc furnaces in real time, capturing the electricity demand during equipment startup, shutdown, and full-load operation; in the cement industry, the fluctuations in the instantaneous power of rotary kilns and grinding equipment can reveal their operating status, helping to identify abnormal power fluctuations; in the aluminum electrolysis industry, the instantaneous power is used to monitor the instantaneous power output of electrolytic cells in real time, especially when adjusting the current of electrolytic cells, capturing the instantaneous changes in energy consumption.

[0250] In this article, the calculation formula for the average power is shown as follows:

[0251]

[0252] Wherein, P avg represents the average power; T represents the length of the time period, with the unit of second (s); P(t) is the instantaneous power of the production equipment. In the iron and steel industry, during long-term monitoring, it is used to measure the average power of electric arc furnaces or rolling mills, optimize the equipment operation strategy, and reduce unnecessary energy consumption fluctuations; in the cement industry, it is used to evaluate the long-term average power consumption of rotary kilns and vertical mills, helping to adjust the equipment load and improve the overall energy efficiency; in the aluminum electrolysis industry, it is used to analyze the long-term operating power of rectification equipment and electrolytic cells, ensuring stable current load and reducing unnecessary power losses.

[0253] For continuous production equipment in the iron and steel, cement, and aluminum electrolysis industries, such as blast furnaces and converters in iron and steel, rotary kilns in cement, and electrolytic cells in aluminum electrolysis, the operating power of these equipment must be kept stable throughout the production cycle. Power fluctuations will not only affect the normal operation of the equipment, but may also lead to a decline in production efficiency and even damage to the equipment. Therefore, minimizing the power load fluctuations becomes a key optimization goal. Thus, the calculation formula for the data of minimizing the power load fluctuations is:

[0254]

[0255] Wherein, f a is the optimization objective function of the equipment power, aiming to minimize the power load fluctuations during the equipment operation, C c is the power cost of the production processing task c (such as production, processing, manufacturing, etc. tasks), ω c is the power usage of the production processing task c within a certain time period, Ω c is the additional penalty when the power load fluctuates (the additional penalty refers to not meeting the constraints of power grid security and stable operation or power market reporting volume and price quotes, etc.).

[0256] The start-stop behavior of equipment power is particularly crucial in the steel industry, especially for high-energy-consuming equipment such as blast furnaces and converters. A large amount of energy is consumed during their startup and shutdown processes, so reasonable control must be carried out. Therefore, the calculation formula for the start-stop constraint time of the power is as follows:

[0257] t start = t c + T setup

[0258] t stop = t c + T end

[0259] In the formula, t start is the time when the equipment starts, t c is the production operation time of the equipment in the stable state (i.e., the normal working state), T setup is the adjustment time for the equipment to change from the initial state S setup to the stable working state S steady ; t stop is the time when the equipment stops, and T end is the time for the equipment to change from the stable working state S steady to the shutdown state S end .

[0260] The running time of the equipment within a production cycle is crucial. The power must remain relatively stable during the running time of the equipment and gradually decrease to the base load after the production task is completed. Therefore, the calculation formula for the continuous operation constraint time of the power is as follows:

[0261]

[0262] In the formula, γ c is the proportion of the production and processing task c in the running time of the equipment; T c is the total running time of the production and processing task c.

[0263] In the above technical solution, the real-time running power data of the equipment also includes the cumulative energy consumption of the equipment. The cumulative energy consumption is used to calculate the total energy consumption of the equipment within a certain period of time and is calculated by integrating the power over time. The formula is as follows:

[0264]

[0265] In the formula, E(t) represents the cumulative energy consumption, with the unit of joule (J) or kilowatt-hour (kWh); P(t) represents the instantaneous power, with the unit of watt (W); and t represents the time variable, with the unit of second (s).

[0266] In the actual operation of the equipment, energy consumption often needs to be calculated in stages. Therefore, the cumulative energy consumption can be extended to piecewise integration, and the formula is as follows:

[0267]

[0268] In the formula, E(t) represents the cumulative energy consumption, with the unit of joule (J) or kilowatt-hour (kWh); P(t) represents the instantaneous power, with the unit of watt (W); t represents the time variable, with the unit of second (s); n is the number of time periods; t i is the demarcation point of each time period. In the iron and steel industry, the total energy consumption of blast furnaces and continuous casters is accumulated to evaluate the energy consumption of each process during smelting; in the cement industry, the cumulative energy consumption of each stage during the continuous operation of ball mills and grinding equipment is calculated to optimize the equipment production scheduling and operation rhythm; in the electrolytic aluminum industry, the cumulative energy consumption is used to calculate the total energy consumption of electrolytic cells during long-term operation to help improve the power dispatching strategy.

[0269] The real-time operating power data of the equipment obtained by the energy consumption and operating parameter acquisition module provides basic data support for the double-layer optimal scheduling module. Through the real-time operating power data of the equipment, the double-layer optimal scheduling module can accurately grasp the energy consumption demand and change trend of the equipment, reasonably arrange the start-stop sequence and operating time period of the equipment, so as to realize the optimal distribution of the overall power and achieve the purpose of energy conservation, loss reduction and efficiency improvement. For example, when the energy consumption and operating parameter acquisition module monitors that the power of a certain key equipment fluctuates violently during a specific period, the double-layer optimal scheduling module can adjust the operation plan of other associated equipment in advance to avoid power impact, ensure the stable operation of the system, and accurately calculate the total power capacity required according to the power demand.

[0270] For the production equipment in high-energy-consuming industries such as iron and steel, cement, and electrolytic aluminum, it is crucial to analyze their power characteristics and carbon emission characteristics. These industries consume a large amount of energy during the production process, resulting in a relatively high carbon emission level. The real-time operating power data of the equipment provided by the energy consumption and operating parameter acquisition module is the basis for the carbon emission analysis module; the instantaneous power, average power, and the curve of power change over time obtained by the energy consumption and operating parameter acquisition module are the key inputs for calculating carbon emissions. For example, by multiplying the instantaneous power by the unit time and combining the known carbon emission factor per unit power, the carbon emissions of the equipment at each moment can be accurately calculated, providing real-time and accurate data support for carbon emission calculation. The carbon emission data calculated by the carbon emission analysis module, in turn, can provide a new perspective for the energy consumption and operating parameter acquisition module. When it is found that the carbon emissions of a certain equipment increase abnormally during a specific period, the energy consumption and operating parameter acquisition module can trace back and check the power fluctuation and operating stability of the equipment during this period to determine whether there are factors such as equipment failures and abnormal operating conditions leading to unreasonable power utilization and thus out-of-control carbon emissions, realizing the dynamic collaborative analysis of the two sets of data.

[0271] In the above technical solution, the calculation formula for obtaining the real-time carbon emission data of the equipment used in the production process according to the real-time operating power data and carbon emission factors of the equipment is as follows:

[0272] E co2 = P total × EF × t

[0273] In the formula, E co2 is the carbon emission, with the unit of ton; P total is the total power load, EF is the carbon emission factor, and t is the fuel usage time; among them, the carbon emission factor is usually determined according to the fuel type and usage efficiency of the equipment. Specifically, the fuel type is one of the core factors affecting the carbon emission factor. Different fuels will produce different amounts of greenhouse gases during combustion or use. For example, the combustion of fossil fuels such as coal, oil, and natural gas will produce a large amount of carbon dioxide, while biomass fuels may produce relatively low carbon emissions under certain conditions. Therefore, the fuel type is crucial for accurately calculating the carbon emission factor. Secondly, the usage efficiency of the equipment is also an important factor affecting the carbon emission factor. High-efficiency equipment requires less fuel for the same output, so the greenhouse gas emissions generated are also correspondingly reduced. On the contrary, low-efficiency equipment may require more fuel to achieve the same output, resulting in higher greenhouse gas emissions. Therefore, the energy efficiency level of the equipment also has an important impact on the determination of the carbon emission factor, with the unit of ton CO2 / MWh.

[0274] In the above technical solution, the calculation formula for the total power load is as follows:

[0275] P total = P base + P var

[0276] In the formula, P total is the total power load (a function of time), with the unit of kW; P base is the base power, that is, the fixed power load of the equipment in the no-load state (the power of the equipment when it is idling); P var is the variable power, which changes with different production conditions.

[0277] In this article, the steel industry is one of the main sources of energy consumption and carbon emissions. The main production equipment includes blast furnaces, converters, electric furnaces, etc. Among them, the carbon emissions of blast furnaces mainly come from the combustion process of fuels such as coal and coke, and its carbon emission characteristics can be estimated by the following formula:

[0278]

[0279] In the formula, E CO2-HFis the total carbon emissions of the blast furnace; M coal , M coke are the masses of coal and coke respectively; H eff is the fuel utilization efficiency of the blast furnace; R recovery is the waste heat recovery coefficient; F CO2-coke , F CO2-coal are the carbon emission factors of coke and coal respectively; η heat is the thermal efficiency of the blast furnace. This formula calculates the total carbon emissions of the blast furnace when using coal and coke, taking into account waste heat recovery and fuel utilization efficiency, and can effectively evaluate the environmental impact of the blast furnace. The carbon emission factors of coal and coke reflect the environmental burden of the fuel.

[0280] An electric arc furnace uses electric energy for steel production, and its carbon emissions mainly come from electricity consumption and a small amount of electrode loss. The carbon emission model of the electric arc furnace is:

[0281]

[0282] In the formula, E CO2-EAF is the total carbon emissions of the electric arc furnace; P elec is the electric power of the electric arc furnace; t run is the working time of the electric arc furnace; F elec is the carbon emission coefficient of electricity; M electrode is the mass of the consumed electrode material; η electrode is the electrode consumption frequency; F CO2-electrode is the carbon emission factor of electrode consumption. This formula reflects the carbon emission characteristics of the electric arc furnace under the consumption of electric energy and electrode materials, facilitating the analysis of the impact of the power source on emissions. The consumption efficiency of the electrode and its carbon emission factor enable enterprises to evaluate the optimization plan for electrode use.

[0283] A converter is a key equipment for converting pig iron into steel, and its carbon emissions mainly come from the reaction process of fuel and hot metal. The carbon emission model of the converter is:

[0284] E CO2-BOF =(M scrap ×F CO2-scrap +P fuel ×F CO2-fuel )×t toperation

[0285] In the formula, E CO2-BOF is the total carbon emissions of the converter, in tons / CO2; M scrap is the mass of scrap steel, in tons; F CO2-scrap is the carbon emission factor of scrap steel; F CO2-fuel is the carbon emission factor of fuel; P fuel is the fuel power used by the converter; t toperationis the operating time of the converter. This formula comprehensively considers the carbon emissions of scrap steel and fuel and is applicable to evaluating the carbon emission characteristics of the converter under different production conditions.

[0286] The carbon emission analysis module inputs the carbon emission data of high-energy-consuming industries into the two-layer optimal scheduling module, which becomes one of the important constraint conditions of the optimization objective function. When the scheduling module arranges equipment scheduling, it not only considers power balance and production efficiency but also takes into account the minimization of carbon emissions, prompting high-energy-consuming enterprises to develop towards the direction of green and low-carbon while meeting production requirements. For example, when formulating a scheduling plan, give priority to arranging the operation of equipment with low carbon emissions and make load reduction or peak-shifting operation adjustments for high-carbon-emission equipment.

[0287] In the above technical solution, the specific method for adjusting the production process to make the energy consumption data of the production process and the real-time carbon emission data of the equipment reach the preset value is as follows: Consider power balance and production efficiency, and also take into account the minimization of carbon emissions, prompting high-energy-consuming enterprises to develop towards the direction of green and low-carbon while meeting production requirements.

[0288] In this article, after the upper-layer central controller in the two-layer optimal scheduling module receives the work instruction sent by the power grid hourly, taking the power grid power demand of the equipment as the balance constraint and the minimum hourly power generation cost as the objective function, it distributes the power grid power demand of the equipment according to the power at each moment and the cost of each aggregation area of each aggregation area.

[0289] In the above technical solution, the specific method for taking the power grid power demand of the equipment as the balance constraint and the minimum power generation cost set by the aggregator during a period as the objective function and distributing the power grid power demand of the equipment according to the power at each moment and the cost of each aggregation area of each aggregation area is as follows: Calculate the total power capacity of each distributed source load in the aggregation area through the power grid power demand of the equipment, calculate the power generation cost of each aggregation area according to the total power capacity of each distributed source load in the aggregation area, and take the minimum hourly power generation cost as the objective function and the maximum and minimum output conditions of the aggregation area as the constraint conditions to distribute the power grid power demand of the equipment.

[0290] In the above technical solution, the calculation formula for calculating the total power capacity of each distributed source load in the aggregation area through the power grid power demand of the equipment is as follows:

[0291]

[0292] In the formula, represents the total output of the distributed photovoltaic power generation equipment at the t-th moment in the i-th aggregation area, represents the predicted output power of the pv i-th distributed photovoltaic power generation equipment at the t-th moment in the i-th aggregation area,

[0293]

[0294] In the formula, represents the total output of the distributed wind power generation equipment at the t-th moment in the i-th aggregation area, represents the predicted output power of the wp i-th distributed wind power generation equipment at the t-th moment in the i-th aggregation area,

[0295]

[0296] In the formula, represents the total output of the distributed traditional generator set equipment at the t-th moment in the i-th aggregation area, represents the ge rated output capacity of the i-th traditional generator set equipment in the i-th aggregation area,

[0297]

[0298] In the formula, represents the total output of the distributed energy storage equipment at the t-th moment in the i-th aggregation area, represents the bat maximum output capacity of the i-th distributed energy storage equipment in the i-th aggregation area,

[0299]

[0300] In the formula, represents the total output of the adjustable load equipment at the t-th moment in the i-th aggregation area, represents the fleload rated output capacity of the i-th adjustable load in the i-th aggregation area,

[0301] In the above technical solution, the calculation formula for the power generation cost of each aggregation area according to the total power capacity of each distributed source and load in the aggregation area is as follows:

[0302]

[0303] In the formula, is the power generation cost at the t-th moment in the i-th aggregation area, is the output cost of the distributed photovoltaic power generation equipment at the t-th moment, is the output cost of the distributed wind power generation equipment at the t-th moment, is the output cost of the traditional generator set equipment at the t-th moment, is the output cost of the distributed energy storage device at the t-th moment, is the output cost of the adjustable load device at the t-th moment, represents the total output of the distributed photovoltaic power generation device in the i-th aggregation area at the t-th moment, represents the total output of the distributed wind power generation device in the i-th aggregation area at the t-th moment, represents the total output of the distributed traditional generator set device in the i-th aggregation area at the t-th moment, represents the total output of the distributed energy storage device in the i-th aggregation area at the t-th moment, represents the total output of the adjustable load device in the i-th aggregation area at the t-th moment.

[0304] In the above technical solution, the calculation formula with the minimum hourly power generation cost as the objective function is:

[0305]

[0306] In the formula, min F t is the minimum power generation cost of the aggregator, is the decision variable, representing the allocated power value of the aggregation area i at the t-th moment, is the power generation cost in the i-th aggregation area at the t-th moment;

[0307] The calculation formulas for the maximum and minimum output conditions of the aggregation area as constraint conditions are shown as follows:

[0308]

[0309] In the formula, P t i ·max represents the maximum output condition of the aggregation area i at the t-th moment, represents the total output of the distributed photovoltaic power generation device in the i-th aggregation area at the t-th moment, represents the total output of the distributed wind power generation device in the i-th aggregation area at the t-th moment, represents the maximum power capacity of the total output of the conventional generator set, represents the total output of the distributed energy storage device in the i-th aggregation area at the t-th moment, represents the total output of the adjustable load device in the i-th aggregation area at the t-th moment;

[0310]

[0311] In the formula, P t i ·min represents the minimum output condition of the aggregation area i at the t-th moment, represents the total output of the distributed photovoltaic power generation device in the i-th aggregation area at the t-th moment, represents the total output of distributed wind power generation equipment at the t-th moment in the i-th aggregation area, represents the minimum power capacity of the total output of conventional generating units, represents the total output of distributed energy storage equipment at the t-th moment in the i-th aggregation area, represents the total output of adjustable load equipment at the t-th moment in the i-th aggregation area.

[0312] In the above technical solution, the calculation formula for the maximum power capacity of the total output of conventional generating units is:

[0313]

[0314] In the formula, represents the maximum power capacity of the total output of conventional generating units, is the maximum output of the i-th conventional generating unit at the t-th moment in the i-th aggregation area, ge

[0315] The calculation formula for the minimum power capacity of the total output of conventional generating units is:

[0316]

[0317] In the formula, represents the minimum power capacity of the total output of conventional generating units, is the minimum output of the i-th conventional generating unit at the t-th moment in the i-th aggregation area, ge

[0318] The decision variable simultaneously satisfies the maximum and minimum value constraints and the supply-demand balance constraint. Among them, the calculation formula for the decision variable to satisfy the maximum and minimum value constraints is as follows:

[0319]

[0320] In the formula, is the decision variable, representing the allocated power value of aggregation area i at the t-th moment, represents the maximum value of the decision variable, represents the minimum value of the decision variable;

[0321] Among them, the calculation formula for the decision variable to satisfy the supply-demand balance constraint is as follows:

[0322]

[0323] In the formula, is the decision variable, Demand-day t is the power allocated by the power grid to each distributed source and load in the aggregation area at the t-th moment.​​

[0324] In this article, after receiving the work instructions allocated by the upper-layer central controller on an hourly basis, the centralized controller at the lower layer of the double-layer optimal scheduling module redistributes the power demand of the power grid allocated to each aggregation area, based on the working characteristics and generation costs of each distributed resource within the aggregation area, with the power demand of the power grid allocated to each aggregation area as the balance constraint and the lowest generation cost during the set time period of each aggregation area as the objective function.

[0325] In the above technical solution, the calculation formula with the power demand of the power grid allocated to each aggregation area as the balance constraint is as follows:

[0326]

[0327] In the formula, is the output situation of the i-th aggregation area at the t-th moment, is the allocated output situation of the i-th distributed photovoltaic power generation device in the i-th aggregation area at the t-th moment, pv is the allocated output situation of the i-th distributed wind power generation device in the i-th aggregation area at the t-th moment, pv is the allocated output situation of the i-th traditional generator set device in the i-th aggregation area at the t-th moment, ge is the allocated output situation of the i-th distributed energy storage device in the i-th aggregation area at the t-th moment, bat is the allocated output situation of the i-th adjustable load in the i-th aggregation area at the t-th moment, fleload

[0328] In the above technical solution, the calculation formula with the lowest generation cost during the set time period of each aggregation area as the objective function is:

[0329]

[0330] In the formula, min f t i represents the lowest generation cost of the i-th aggregation area at the t-th moment, represents the decision variable of the i-th distributed photovoltaic power generation device in the i-th aggregation area at the t-th moment, pv represents the decision variable of the i-th distributed wind power generation device in the i-th aggregation area at the t-th moment, wp ​​​​​​​represents the decision variable of the i-th conventional generator set at the t-th moment in the i-th aggregation area, ge and represents the decision variable of the i-th distributed energy storage device at the t-th moment in the i-th aggregation area, bat and represents the decision variable of the i-th adjustable load device at the t-th moment in the i-th aggregation area, fleload and is the output cost of the distributed photovoltaic power generation device at the t-th moment, is the output cost of the distributed wind power generation device at the t-th moment, is the output cost of the conventional generator set at the t-th moment, is the output cost of the distributed energy storage device at the t-th moment, is the output cost of the adjustable load device at the t-th moment.

[0331] In the above technical solution, since distributed photovoltaics and distributed wind power are non-dispatchable power sources, their output conditions can be defined according to the distributed energy constraints. Specifically, the output condition allocated to the i-th distributed photovoltaic power generation device at the t-th moment in the i-th aggregation area satisfies the following formula: pv

[0332]

[0333] In the formula, is the output condition allocated to the i-th distributed photovoltaic power generation device at the t-th moment in the i-th aggregation area, pv represents the predicted output power of the i-th distributed photovoltaic power generation device at the t-th moment in the i-th aggregation area, pv represents the variable of distributed photovoltaic power generation, with a value range of 0 to 1, indicating whether the distributed resource operates according to the predicted power at this moment;

[0334] The output condition allocated to the i-th distributed wind power generation device at the t-th moment in the i-th aggregation area satisfies the following formula: pv

[0335]

[0336] In the formula, is the output condition allocated to the i-th distributed wind power generation device at the t-th moment in the i-th aggregation area, pv represents the predicted output power of the i-th distributed wind power generation device at the t-th moment in the i-th aggregation area, wp ​​​​​​A variable representing distributed wind power, with a value range of 0 to 1, indicating whether the distributed resource is operating at the predicted power at this moment.

[0337] In the above technical solution, the conventional generator set, distributed energy storage, and flexible load are dispatchable power sources. Among them, the constraint conditions of the conventional generator set and distributed energy storage are the same as those of the upper-layer dispatch model, and the output of the flexible load conforms to the maximum and minimum value constraints. Specifically, the output of the i-th adjustable load in the i-th aggregation area at the t-th moment conforms to the maximum and minimum value constraint conditions, and the maximum and minimum value constraint conditions are shown in the following formula: fleload For the i-th adjustable load allocated in the i-th aggregation area at the t-th moment, its output conforms to the maximum and minimum value constraint conditions, and the maximum and minimum value constraint conditions are as follows:

[0338]

[0339] In the formula, is the output of the i-th adjustable load allocated in the i-th aggregation area at the t-th moment, fleload and represents the maximum output of the adjustable load.

[0340] Embodiment 3

[0341] A computer-readable storage medium stores a computer program, characterized in that: when the computer program is executed by a processor, it implements the steps of the above method.

[0342] The load feature extraction method of the present invention based on big data analysis and machine learning model driving can accurately predict electricity demand through accurate extraction and clustering of load features, and adjust the device power in real time. It can help users identify peak energy consumption, optimize the device operation strategy, thereby significantly improving energy utilization efficiency, reducing energy consumption costs, while optimizing power resource allocation, promoting load transfer and peak shaving and valley filling. This method improves energy utilization efficiency and reduces carbon emissions and pollution.

[0343] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer-readable storage media. Therefore, the present invention can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can adopt the form of a computer-readable storage medium implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0344] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer-readable storage media according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate a system for implementing the functions specified in one or more flows Figure 1 or more flows and / or blocks Figure 1 or more blocks.

[0345] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction system that implements the functions specified in one or more flows Figure 1 or more flows and / or blocks Figure 1 or more blocks.

[0346] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows Figure 1 or more flows and / or blocks Figure 1 or more blocks.

[0347] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit the scope of its protection. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that after reading the present invention, various changes, modifications, or equivalent replacements can still be made to the specific implementation manners of the invention, but these changes, modifications, or equivalent replacements are all within the scope of the claims of the invention pending approval.

[0348] Contents not described in detail in this specification belong to the prior art well-known to those of ordinary skill in the art.

Claims

1. A multi-objective autonomous optimization and regulation system for high-energy-consuming industrial loads, characterized in that: It includes an energy consumption and operating parameter acquisition module, a carbon emission analysis module, and a two-layer optimal scheduling module; The energy consumption and operating parameter acquisition module is used to acquire the energy consumption data of the production process and the real-time operating power data of the equipment used in the production process; The carbon emission analysis module obtains the real-time carbon emission data of the equipment used in the production process based on the real-time operating power data of the equipment and the carbon emission factor; The two-layer optimal scheduling module adjusts the production process to make the energy consumption data of the production process and the real-time carbon emission data of the equipment reach the preset values, and obtains the grid power demand of the equipment used in the adjusted production process; taking the grid power demand of the equipment as the balance constraint and the minimum power generation cost set by the aggregator during the set period as the objective function, the grid power demand of the equipment is allocated according to the power at each moment and the aggregator area cost of each aggregator area, and then taking the grid power demand after allocation of each aggregator area as the balance constraint and the minimum power generation cost set by each aggregator area during the set period as the objective function, the grid power demand after allocation of each aggregator area is allocated again.

2. The multi-objective autonomous optimization regulation system for high-energy-consuming industrial loads according to claim 1, characterized in that: The real-time operating power data of the equipment includes instantaneous power, average power, data for minimizing the volatility of the power load, start-stop constraint time of the power, and continuous operation constraint time of the power. Among them, the calculation formula for the data for minimizing the volatility of the power load is: where f a is the optimization objective function of the device power, and the goal is to minimize the power load volatility during the device operation. C c is the power cost of the production task c, ω c is the power consumption of the production task c within a certain time period, and Ω c is the additional penalty when the power load fluctuates; The calculation formula for the start-stop constraint time of the power is: t start = t c + T setup t stop = t c + T end where t start is the time at the start of the device, t c is the production operation time in the stable state of the device, T setup is the adjustment time of the device from the initial state to the stable working state, t stop is the time when the device stops, T end is the time of the device from the stable working state to the shutdown state; The calculation formula for the continuous operation constraint time of the power is: where γ c is the proportion of production and processing task c in the equipment operation time; T c is the total operation time of production and processing task c.

3. The multi-objective autonomous optimization and regulation system for high-energy-consuming industrial loads according to claim 2, characterized in that: The calculation formula for obtaining the real-time carbon emission data of the equipment used in the production process based on the real-time operating power data of the equipment and the carbon emission factor is as follows: E co2 = P total × EF × t where E co2 is the carbon emission, P total is the total power load, EF is the carbon emission factor, and t is the fuel usage time; Among them, the calculation formula for the total power load is as follows: P total = P base + P var Wherein, P total is the total power load, P base is the base power, and P var is the variable power.

4. The multi-objective autonomous optimization and regulation system for high-energy-consuming industrial loads according to claim 3, wherein: Taking the grid power demand of the equipment as the balance constraint and the minimum power generation cost set by the aggregator during the set period as the objective function, the specific method for allocating the grid power demand of the equipment according to the power at each moment and the aggregator area cost of each aggregator area is: calculating the total power capacity of each distributed source and load in the aggregator area through the grid power demand of the equipment, calculating the power generation cost of each aggregator area according to the total power capacity of each distributed source and load in the aggregator area, and taking the minimum power generation cost per hour as the objective function and the maximum and minimum output conditions of the aggregator area as the constraint conditions to allocate the grid power demand of the equipment.

5. The multi-objective autonomous optimization and regulation system for high-energy-consuming industrial loads according to claim 4, characterized in that: The calculation formula for calculating the total power capacity of each distributed source and load in the aggregator area through the grid power demand of the equipment is as follows: In the formula, represents the total output of the distributed photovoltaic power generation equipment at the t-th moment in the i-th aggregation area, represents the predicted output power of the pv i-th distributed photovoltaic power generation equipment at the t-th moment in the i-th aggregation area, In the formula, represents the total output of the distributed wind power generation equipment at the t-th moment in the i-th aggregation area, represents the predicted output power of the wp i-th distributed wind power generation equipment at the t-th moment in the i-th aggregation area, In the formula, represents the total output of the distributed traditional generator sets at the t-th moment in the i-th aggregation area, represents the i-th ge rated output capacity of the traditional generator sets in the i-th aggregation area, In the formula, represents the total output of the distributed energy storage device at the t-th moment in the i-th aggregation area, represents the i-th bat maximum output capacity of the distributed energy storage devices in the aggregation area, In the formula, represents the total output of the adjustable load device at the t-th moment in the i-th aggregation area, represents the i-th fleload rated output capacity of the adjustable load, The calculation formula for calculating the power generation cost of each aggregator area according to the total power capacity of each distributed source and load in the aggregator area is as follows: In the formula, is the power generation cost at the t-th moment in the i-th aggregation area, is the output cost of the distributed photovoltaic power generation equipment at the t-th moment, is the output cost of the distributed wind power generation equipment at the t-th moment, is the output cost of the traditional generator set equipment at the t-th moment, is the output cost of the distributed energy storage equipment at the t-th moment, is the output cost of the adjustable load equipment at the t-th moment, represents the total output of the distributed photovoltaic power generation equipment at the t-th moment in the i-th aggregation area, represents the total output of the distributed wind power generation equipment at the t-th moment in the i-th aggregation area, represents the total output of the distributed traditional generator set equipment at the t-th moment in the i-th aggregation area, represents the total output of the distributed energy storage equipment at the t-th moment in the i-th aggregation area, represents the total output of the adjustable load equipment at the t-th moment in the i-th aggregation area; The calculation formula for taking the minimum power generation cost per hour as the objective function is: where, min F t is the minimum power generation cost of the aggregator, is a decision variable representing the allocated power value of the aggregation area i at time t, is the power generation cost of the i-th aggregation area at the t-th moment; The calculation formula for taking the maximum and minimum output conditions of the aggregator area as the constraint conditions is as follows: In the formula, represents the maximum output of the aggregation area i at time t, represents the total output of the distributed photovoltaic power generation equipment in the i-th aggregation area at time t, represents the total output of the distributed wind power generation equipment in the i-th aggregation area at time t, represents the maximum power capacity of the total output of the conventional generator set, represents the total output of the distributed energy storage equipment in the i-th aggregation area at time t, represents the total output of the adjustable load equipment in the i-th aggregation area at time t; In the formula, represents the minimum output of the aggregation area i at time t, represents the total output of the distributed photovoltaic power generation equipment in the i-th aggregation area at the t-th moment, represents the total output of the distributed wind power generation equipment in the i-th aggregation area at the t-th moment, represents the minimum power capacity of the total output of the conventional generator sets, represents the total output of the distributed energy storage equipment in the i-th aggregation area at the t-th moment, represents the total output of the adjustable load equipment in the i-th aggregation area at the t-th moment.

6. The multi-objective autonomous optimization and regulation system for high-energy-consuming industrial loads according to claim 5, characterized in that: The calculation formula for the maximum power capacity of the total output of the conventional generator set is: wherein, represents the maximum power capacity of the total output of a conventional power generation set, is the maximum output of the i-th conventional power generation set at the t-th moment in the i-th aggregation area, ge and The calculation formula for the minimum power capacity of the total output of the conventional generator set is: In the formula, represents the minimum power capacity of the total output of a conventional generating unit, is the minimum output of the ge ith conventional generating unit at the t-th moment in the i-th aggregation area, The decision variable simultaneously satisfies the maximum and minimum value constraints and the supply-demand balance constraint. Among them, the calculation formula for the decision variable to satisfy the maximum and minimum value constraints is: In the formula, is a decision variable, representing the allocated power value of the aggregation area i at time t, represents the maximum value of the decision variable, represents the minimum value of the decision variable; Among them, the calculation formula for the decision variable to satisfy the supply-demand balance constraint is: In the formula, is the decision variable, and Demand-dayt is the power allocated by the power grid to each distributed source and load in the aggregation area at time t.

7. The multi-objective autonomous optimization and regulation system for high-energy-consuming industrial loads according to claim 6, characterized in that: The calculation formula with the power demand of the power grid after distribution in each aggregation area as the balance constraint is as follows: Wherein, is the output of the i-th aggregation area at the t-th moment, is the output assigned to the pv th distributed photovoltaic power generation device in the i-th aggregation area at the t-th moment, is the output assigned to the pv th distributed wind power generation device in the i-th aggregation area at the t-th moment, is the output assigned to the ge th traditional generator set device in the i-th aggregation area at the t-th moment, is the output assigned to the bat th distributed energy storage device in the i-th aggregation area at the t-th moment, is the output assigned to the fleload th adjustable load in the i-th aggregation area at the t-th moment, The calculation formula with the lowest power generation cost in the set time period of each aggregation area as the objective function is: In the formula, represents the minimum power generation cost at the t-th moment in the i-th aggregation area, represents the decision variable of the pv i-th distributed photovoltaic power generation device at the t-th moment in the i-th aggregation area, represents the decision variable of the wp i-th distributed wind power generation device at the t-th moment in the i-th aggregation area, represents the decision variable of the ge i-th traditional generator set device at the t-th moment in the i-th aggregation area, represents the decision variable of the bat i-th distributed energy storage device at the t-th moment in the i-th aggregation area, represents the decision variable of the fleload i-th adjustable load device at the t-th moment in the i-th aggregation area, is the output cost of the distributed photovoltaic power generation device at the t-th moment, is the output cost of the distributed wind power generation device at the t-th moment, is the output cost of the traditional generator set device at the t-th moment, is the output cost of the distributed energy storage device at the t-th moment, is the output cost of the adjustable load device at the t-th moment.

8. The multi-objective autonomous optimization and regulation system for high-energy-consuming industrial loads according to claim 7, characterized in that: The output power distribution of the pv i-th distributed photovoltaic power generation device at the t-th moment in the i-th aggregation area satisfies the following formula: In the formula, is the output power allocated to the pv ith distributed photovoltaic power generation device at the tth moment in the ith aggregation area, represents the predicted output power of the pv ith distributed photovoltaic power generation device at the tth moment in the ith aggregation area, represents the variable of distributed photovoltaic power generation, and its value ranges from 0 to 1; The output power distribution of the pv ith distributed wind power generation equipment at the tth moment in the ith aggregation area satisfies the following formula: In the formula, is the output of the i-th distributed wind power generation device at the t-th moment in the i-th aggregation area, pv and represents the predicted output power of the i-th distributed wind power generation device at the t-th moment in the i-th aggregation area, wp while represents the variable of distributed wind power generation, taking values from 0 to 1. The output situation of the $i$-th adjustable load allocated at the $t$-th moment in the $i$-th aggregation area conforms to the extreme value constraint condition, and its extreme value constraint condition is shown as follows: fleload The output situation of the $i$-th adjustable load allocated at the $t$-th moment in the $i$-th aggregation area conforms to the extreme value constraint condition, and its extreme value constraint condition is shown as follows: In the formula, is the output situation allocated to the i-th adjustable load at the t-th moment in the i-th aggregation area, fleload and represents the maximum output of the adjustable load. ​ 9. A multi-objective autonomous optimization regulation method for high-energy-consuming industrial loads, characterized in that: It includes the following: Obtain the energy consumption data of the production process and the real-time operating power data of the equipment used in the production process; Obtain the real-time carbon emission data of the equipment used in the production process according to the real-time operating power data of the equipment and the carbon emission factor; Adjust the production process to make the energy consumption data of the production process and the real-time carbon emission data of the equipment reach the preset values, and obtain the power grid power demand of the equipment used in the adjusted production process; taking the power grid power demand of the equipment as the balance constraint and the lowest power generation cost in the set time period of the aggregator as the objective function, distribute the power grid power demand of the equipment according to the power at each moment and the area cost of each aggregation area, and then take the power grid power demand after distribution in each aggregation area as the balance constraint and the lowest power generation cost in the set time period of each aggregation area as the objective function, and redistribute the power grid power demand after distribution in each aggregation area.

10. The multi-objective autonomous optimization regulation method for high-energy-consuming industrial loads according to claim 9, wherein: The real-time operating power data of the equipment includes instantaneous power, average power, data for minimizing the volatility of the power load, start-stop constraint time of the power, and continuous operation constraint time of the power. Among them, the calculation formula for the data for minimizing the volatility of the power load is: where f a is the optimization objective function of the device power, and the goal is to minimize the volatility of the power load during the operation of the device. C c is the power cost of the production task c, ω c is the power consumption of the production task c within a certain time period, and Ω c is the additional penalty when the power load fluctuates; The calculation formula for the start-stop constraint time of the power is: t start = t c + T setup t stop = t c + T end where t start is the time at the start of equipment startup, t c is the production operation time in the stable state of the equipment, T setup is the adjustment time of the equipment from the initial state to the stable working state, t stop is the time at the stop of the equipment, T end is the time of the equipment from the stable working state to the shutdown state; The calculation formula for the continuous operation constraint time of the power is: where γ c is the proportion of production and processing task c in the equipment operation time; T c is the total operation time of production and processing task c.

11. The multi-objective autonomous optimization regulation method for high-energy-consuming industrial loads according to claim 10, characterized in that: The calculation formula for obtaining the real-time carbon emission data of the equipment used in the production process according to the real-time operating power data of the equipment and the carbon emission factor is as follows: E co2 = P total × EF × t Where E co2 is the carbon emission, P total is the total power load, EF is the carbon emission factor, and t is the fuel usage time; Among them, the calculation formula for the total power load is as follows: P total = P base + P var Where, P total is the total power load, P base is the base power, and P var is the variable power.

12. The multi-objective autonomous optimization regulation method for high-energy-consuming industrial loads according to claim 11, wherein: The specific method for distributing the power grid power demand of the equipment with the power grid power demand of the equipment as the balance constraint and the lowest power generation cost in the set time period of the aggregator as the objective function according to the power at each moment and the area cost of each aggregation area is: calculate the total power capacity of each distributed source load in the aggregation area through the power grid power demand of the equipment, calculate the power generation cost of each aggregation area according to the total power capacity of each distributed source load in the aggregation area, and take the lowest power generation cost per hour as the objective function and the maximum and minimum output situations of the aggregation area as the constraint conditions to distribute the power grid power demand of the equipment.

13. The multi-objective autonomous optimization regulation method for high-energy-consuming industrial loads according to claim 12, characterized in that: The calculation formula for calculating the total power capacity of each distributed source load in the aggregation area through the power grid power demand of the equipment is as follows: In the formula, represents the total output of the distributed photovoltaic power generation equipment in the i-th aggregation area at the t-th moment, represents the predicted output power of the pv i-th distributed photovoltaic power generation equipment in the i-th aggregation area at the t-th moment, Wherein, represents the total output of the distributed wind power generation equipment at the t-th moment in the i-th aggregation area, represents the predicted output power of the wp -th distributed wind power generation equipment at the t-th moment in the i-th aggregation area, In the formula, represents the total output of the distributed traditional generator sets at the t-th moment in the i-th aggregation area, represents the i-th ge rated output capacity of the traditional generator sets in the i-th aggregation area, In the formula, represents the total output of the distributed energy storage device at the t-th moment in the i-th aggregation area, represents the i-th bat maximum output capacity of the distributed energy storage devices in the i-th aggregation area, In the formula, represents the total output of the adjustable load equipment at the t-th moment in the i-th aggregation area, represents the i-th fleload rated output capacity of the adjustable load, The calculation formula for calculating the power generation cost of each aggregation area according to the total power capacity of each distributed source load in the aggregation area is as follows: Wherein, is the power generation cost of the i-th aggregation area at the t-th moment, is the output cost of the distributed photovoltaic power generation equipment at the t-th moment, is the output cost of the distributed wind power generation equipment at the t-th moment, is the output cost of the traditional generator set equipment at the t-th moment, is the output cost of the distributed energy storage equipment at the t-th moment, is the output cost of the adjustable load equipment at the t-th moment, represents the total output of the distributed photovoltaic power generation equipment in the i-th aggregation area at the t-th moment, represents the total output of the distributed wind power generation equipment in the i-th aggregation area at the t-th moment, represents the total output of the distributed traditional generator set equipment in the i-th aggregation area at the t-th moment, represents the total output of the distributed energy storage equipment in the i-th aggregation area at the t-th moment, represents the total output of the adjustable load equipment in the i-th aggregation area at the t-th moment; The calculation formula with the lowest power generation cost per hour as the objective function is: Where, min F t is the minimum power generation cost of the aggregator, is a decision variable representing the allocated power value of the aggregation area i at time t, is the power generation cost of the i-th aggregation area at the t-th moment; The calculation formula for the maximum and minimum output situations of the aggregation area as the constraint conditions is as follows: Wherein, represents the maximum output of the aggregation area i at time t, represents the total output of the distributed photovoltaic power generation equipment in the i-th aggregation area at the t-th moment, represents the total output of the distributed wind power generation equipment in the i-th aggregation area at the t-th moment, represents the maximum power capacity of the total output of the conventional generator set, represents the total output of the distributed energy storage equipment in the i-th aggregation area at the t-th moment, represents the total output of the adjustable load equipment in the i-th aggregation area at the t-th moment; In the formula, represents the minimum output of the aggregation area i at time t, represents the total output of the distributed photovoltaic power generation equipment in the i-th aggregation area at time t, represents the total output of the distributed wind power generation equipment in the i-th aggregation area at time t, represents the minimum power capacity of the total output of the conventional generator set, represents the total output of the distributed energy storage equipment in the i-th aggregation area at time t, represents the total output of the adjustable load equipment in the i-th aggregation area at time t.

14. The multi-objective autonomous optimization regulation method for high-energy-consuming industrial loads according to claim 13, wherein: The calculation formula for the maximum power capacity of all outputs of the conventional generator set is: In the formula, represents the maximum power capacity of the total output of a conventional generating set, is the maximum output of the ge ith conventional generating set at the tth moment in the ith aggregation area, The calculation formula for the minimum power capacity of all outputs of the conventional generator set is: Wherein, represents the minimum power capacity of the total output of a conventional generating set, is the minimum output of the ge ith conventional generating set at the t-th moment in the i-th aggregation area, The decision variable simultaneously satisfies the maximum and minimum value constraints and the supply-demand balance constraint. Among them, the calculation formula for the decision variable to satisfy the maximum and minimum value constraints is: wherein, is a decision variable, representing the power value allocated to the aggregation area i at time t, represents the maximum value of the decision variable, represents the minimum value of the decision variable; Among them, the calculation formula for the decision variable to satisfy the supply-demand balance constraint is: In the formula, is the decision variable, and Demand-day t is the power allocated by the power grid to each distributed source and load in the aggregation area at time t.

15. The multi-objective autonomous optimization regulation method for high-energy-consuming industrial loads according to claim 14, characterized in that: The calculation formula with the power grid power demand after distribution in each aggregation area as the balance constraint is as follows: Wherein, is the output of the i-th aggregation area at the t-th moment, is the output assigned to the i-th pv distributed photovoltaic power generation device in the i-th aggregation area at the t-th moment, is the output assigned to the i-th pv distributed wind power generation device in the i-th aggregation area at the t-th moment, is the output assigned to the i-th ge conventional generator set device in the i-th aggregation area at the t-th moment, is the output assigned to the i-th bat distributed energy storage device in the i-th aggregation area at the t-th moment, is the output assigned to the i-th fleload adjustable load in the i-th aggregation area at the t-th moment, The calculation formula with the minimum power generation cost in the set time period of each aggregation area as the objective function is: In the formula, represents the minimum power generation cost at the t-th moment in the i-th aggregation area, represents the decision variable of the i-th distributed photovoltaic power generation device at the t-th moment in the i-th aggregation area, pv where i represents the i-th device, represents the decision variable of the i-th distributed wind power generation device at the t-th moment in the i-th aggregation area, wp where i represents the i-th device, represents the decision variable of the i-th traditional generator set device at the t-th moment in the i-th aggregation area, ge where i represents the i-th device, represents the decision variable of the i-th distributed energy storage device at the t-th moment in the i-th aggregation area, bat where i represents the i-th device, represents the decision variable of the i-th adjustable load device at the t-th moment in the i-th aggregation area, fleload where i represents the i-th device, is the output cost of the distributed photovoltaic power generation device at the t-th moment, is the output cost of the distributed wind power generation device at the t-th moment, is the output cost of the traditional generator set device at the t-th moment, is the output cost of the distributed energy storage device at the t-th moment, is the output cost of the adjustable load device at the t-th moment.

16. The multi-objective autonomous optimization regulation method for high-energy-consuming industrial loads according to claim 15, wherein: The output power distribution of the pv ith distributed photovoltaic power generation device at the tth moment in the ith aggregation area satisfies the following formula: In the formula, is the output power allocated to the pv th distributed photovoltaic power generation device at the th moment in the pv th aggregated area, represents the variable of distributed photovoltaic power generation, with a value range of 0 to 1; The output power distribution of the pv ith distributed wind power generation equipment at the tth moment in the ith aggregation area satisfies the following formula: In the formula, is the output power allocated to the pv ith distributed wind power generation equipment at the tth moment in the ith aggregation area, represents the predicted output power of the wp ith distributed wind power generation equipment at the tth moment in the ith aggregation area, represents the variable of distributed wind power generation, and its value ranges from 0 to 1; The output situation of the $i$-th adjustable load allocated at the $t$-th moment in the $i$-th aggregation area meets the extreme value constraint conditions, and its extreme value constraint conditions are shown in the following formula: fleload where the output of the $i$-th adjustable load allocated at the $t$-th moment in the $i$-th aggregation area meets the extreme value constraint conditions, and its extreme value constraint conditions are shown in the following formula: In the formula, is the output situation allocated to the i-th adjustable load at the t-th moment in the i-th aggregation area, fleload and represents the maximum output of the adjustable load. ​ 17. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 9-16.

Images