Method and apparatus for determining light intensity

Abstract

The application discloses a method and device for determining illumination intensity. The method comprises: obtaining an environmental state space parameter in a target area, wherein the environmental state space parameter comprises at least indoor illumination intensity, a current time and a real-time electricity price; obtaining an instant reward and punishment value and an accumulated reward and punishment value according to the environmental state space parameter; obtaining a control instruction according to the instant reward and punishment value and the accumulated reward and punishment value, wherein the control instruction is used for adjusting the illumination intensity of a lighting device; adjusting the illumination intensity in the target area based on the control instruction, and determining a target illumination intensity based on the adjusted illumination intensity. The application solves the technical problem of affecting normal work of a user, wasting of electric energy resources and affecting user experience caused by setting a fixed threshold to adjust the illumination intensity without considering user preference in the related art.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of load regulation, in particular, to a method and device for determining illumination intensity. BACKGROUND

[0002] With the improvement of production and living standards, the power consumption of lighting systems is increasing year by year. Although the proportion of public buildings accounts for less than 5% of the urban building area in China, the proportion of its power consumption is as high as 25%. Therefore, it is an important step to take appropriate energy optimization methods for the lighting system of public buildings to save energy as much as possible on the premise of meeting user comfort, to build a resource-saving society and achieve overall energy saving of buildings.

[0003] Nowadays, the large-scale application of new lighting technologies such as light-emitting diodes (LEDs) and the rapid development of modern lighting technologies. Compared with traditional lighting systems, it has multifunctionality and low energy consumption, has various control options, and can be used for intelligent lighting, which provides the possibility for fully tapping the energy-saving potential of public buildings.

[0004] At present, the information and communication technology (ICT) infrastructure is also constantly innovating and developing, which promotes the application of advanced controllers such as integrated sensors, actuators and microcontrollers to public building lighting systems. The goal of these controllers is to provide artificial light when the user is present and considers that the natural light is insufficient. These systems mainly consist of two parts: detecting indoor users and adjusting indoor light. The light intensity sensor is mainly used in the part of adjusting indoor light, that is, the system automatically turns off the light to save energy when the indoor light is sufficient. According to experimental data, the application of this system can greatly save energy. However, one disadvantage of this daylight-dependent system is that a fixed threshold is usually used to turn on or off without considering the user's preference. This not only greatly reduces the user's comfort, but more seriously, it may affect normal office work and life and disable the system. Therefore, it is an urgent problem to realize energy optimization of public building lighting systems to meet the user's comfort on the basis of saving energy.

[0005] In view of the above problems, no effective solution has been proposed so far. SUMMARY

[0006] The embodiments of the present application provide a method and device for determining illumination intensity, which at least solve the technical problems of affecting normal work of users, wasting energy resources and affecting user experience caused by setting a fixed threshold to adjust the illumination intensity without considering user preferences in the related art.

[0007] According to an aspect of the embodiments of the present application, a method for determining illumination intensity is provided, comprising: obtaining an environmental state space parameter in a target area, wherein the environmental state space parameter comprises at least indoor illumination intensity, current time, and real-time electricity price; obtaining an instant reward and punishment value and an accumulated reward and punishment value according to the environmental state space parameter; obtaining a control instruction according to the instant reward and punishment value and the accumulated reward and punishment value, wherein the control instruction is used to adjust the illumination intensity of a lighting device; adjusting the illumination intensity in the target area based on the control instruction, and determining a target illumination intensity based on the adjusted illumination intensity.

[0008] Optionally, determining the target illumination intensity based on the adjusted illumination intensity comprises: obtaining an initial illumination intensity in the target area after adjusting the illumination intensity in the target area based on the control instruction; determining whether the initial illumination intensity belongs to a comfortable lighting intensity interval corresponding to the target area; in a case where the determination result indicates that the initial illumination intensity belongs to the comfortable lighting intensity interval, determining the initial illumination intensity as the target illumination intensity.

[0009] Optionally, determining the target illumination intensity based on the adjusted illumination intensity further comprises: obtaining an initial illumination intensity in the target area after adjusting the illumination intensity in the target area based on the control instruction; determining whether the initial illumination intensity belongs to a comfortable lighting intensity interval corresponding to the target area; in a case where the determination result indicates that the initial illumination intensity does not belong to the comfortable lighting intensity interval, determining a deviation value corresponding to the initial illumination intensity; determining a deviation level corresponding to the deviation value; adjusting the initial illumination intensity according to the deviation level, wherein the adjusted initial illumination intensity satisfies the comfortable lighting intensity interval; and determining the adjusted initial illumination intensity as the target illumination intensity.

[0010] Optionally, before determining whether the initial illumination intensity belongs to the comfortable lighting intensity interval corresponding to the target area, the method further comprises: obtaining satisfaction data of a plurality of objects in the target area, wherein the satisfaction data is used to indicate a range size of an acceptable illumination intensity of each object in the plurality of objects; and filtering the satisfaction data to obtain the comfortable lighting intensity interval.

[0011] Optionally, filtering the satisfaction data to obtain the comfortable lighting intensity interval comprises: calculating the range size of the acceptable illumination intensity of each object to obtain a maximum illumination intensity value and a minimum illumination intensity value of the range size of the acceptable illumination intensity; and determining a set interval formed by the maximum illumination intensity value and the minimum illumination intensity value as the comfortable lighting intensity interval.

[0012] Optionally, after the satisfaction data is filtered to obtain the comfortable illuminance interval, the method further comprises: determining the comfortable illuminance interval as a first objective function, determining the minimum running cost as a second objective function; determining the lighting energy load as a constraint condition of the first objective function and the second objective function, and optimizing the comfortable illuminance interval and the running cost.

[0013] According to another aspect of the embodiments of the present application, a determination apparatus of illumination intensity is further provided, comprising: an acquisition module, configured to acquire an environmental state space parameter in a target area, wherein the environmental state space parameter comprises at least indoor illumination intensity, current time and real-time electricity price; a first determination module, configured to obtain an instant reward and punishment value and an accumulated reward and punishment value according to the environmental state space parameter; a second determination module, configured to obtain a control instruction according to the instant reward and punishment value and the accumulated reward and punishment value, wherein the control instruction is used to adjust the illumination intensity of a lighting device; and a third determination module, configured to adjust the illumination intensity in the target area based on the control instruction, and determine a target illumination intensity based on the adjusted illumination intensity.

[0014] Optionally, the third determination module comprises: a first determination unit, configured to obtain an initial illumination intensity in the target area after adjusting the illumination intensity in the target area based on the control instruction; a judgment unit, configured to judge whether the initial illumination intensity belongs to a comfortable illuminance interval corresponding to the target area; and a second determination unit, configured to determine the initial illumination intensity as the target illumination intensity in a case that the initial illumination intensity belongs to the comfortable illuminance interval according to a judgment result.

[0015] According to another aspect of the embodiments of the present application, a non-volatile storage medium is further provided, comprising a stored program, wherein the non-volatile storage medium controls a device where the non-volatile storage medium is located to execute any one of the determination methods of illumination intensity when the program is running.

[0016] According to another aspect of the embodiments of the present application, a processor is further provided, wherein the processor is used to run a program, and the processor executes any one of the determination methods of illumination intensity when the program is running.

[0017] In the embodiment of the present application, the light intensity is adjusted based on the environmental state space parameters. The current environmental state space parameters in the target area are obtained, wherein the environmental state space parameters at least include indoor light intensity, current time, and real-time electricity price. The instant reward and punishment value and the cumulative reward and punishment value are obtained according to the environmental state space parameters. The control instruction is obtained according to the instant reward and punishment value and the cumulative reward and punishment value, wherein the control instruction is used to adjust the light intensity of the lighting device. The light intensity in the target area is adjusted based on the control instruction, and the target light intensity is determined based on the adjusted light intensity. The purpose of automatically adjusting the light intensity is achieved, thereby realizing the self-adjustment of the light intensity based on the environmental state space parameters and the like, saving the electric power resources, and further solving the technical problems of affecting the normal work of users, wasting electric power resources, and affecting the user experience caused by setting fixed threshold values to adjust the light intensity in the related art without considering the user preferences. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings, which are included to provide a further understanding of the present application, constitute a part of the present application and illustrate the illustrative embodiments of the present application and their description serve to explain the present application, and do not constitute improper limitations on the present application. In the drawings:

[0019] Figure 1 is a flow diagram of an optional light intensity determination method according to an embodiment of the present application;

[0020] Figure 2 is a framework diagram of an optional public building lighting system load scheduling method according to an embodiment of the present application;

[0021] Figure 3 is a flow diagram of an optional public building lighting system load scheduling method based on reinforcement learning according to an embodiment of the present application;

[0022] Figure 4 is an optional agent neural network structure diagram according to an embodiment of the present application;

[0023] Figure 5 is a structural diagram of an optional light intensity determination device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second", and the like in the description and in the claims of the present application and above-described accompanying drawings are intended to distinguish similar objects and not necessarily for describing a particular sequential or chronological order. It should be understood that the data thus used can be interchanged, where appropriate, so that the embodiments of the present application described herein can be implemented in orders other than those illustrated or described herein. In addition, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or apparatus that includes a list of steps or units as processes, methods, systems, products, or apparatuses do not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to such processes, methods, products, or apparatuses.

[0026] According to an embodiment of the present application, a method for determining illumination intensity is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0027] Figure 1 A method for determining illumination intensity according to an embodiment of the present application is shown in FIG. 1, which includes the following steps: Figure 1

[0028] Step S102, obtaining the current environmental state space parameters in the target area, wherein the environmental state space parameters at least include: indoor illumination intensity, current time, and real-time electricity price;

[0029] Step S104, obtaining the instant reward and punishment value and the cumulative reward and punishment value according to the environmental state space parameters;

[0030] Step S106, obtaining the control instruction according to the instant reward and punishment value and the cumulative reward and punishment value, wherein the control instruction is used to adjust the illumination intensity of the lighting device;

[0031] Step S108, adjusting the illumination intensity in the target area based on the control instruction, and determining the target illumination intensity based on the adjusted illumination intensity.

[0032] ​The method for determining the illumination intensity comprises the following steps: acquiring an environmental state space parameter in a target area, wherein the environmental state space parameter comprises at least indoor illumination intensity, a current time and a real-time electricity price; obtaining an instant reward and punishment value and an accumulated reward and punishment value according to the environmental state space parameter; obtaining a regulation instruction according to the instant reward and punishment value and the accumulated reward and punishment value, wherein the regulation instruction is used to adjust the illumination intensity of a lighting device; adjusting the illumination intensity in the target area based on the regulation instruction, determining a target illumination intensity based on the adjusted illumination intensity, and achieving the purpose of automatically adjusting the illumination intensity, thereby realizing the self-adjustment of the illumination intensity based on the environmental state space parameter and the like, saving the electric resource, and further solving the technical problems of affecting the normal work of users, wasting the electric resource and affecting the user experience caused by setting a fixed threshold to adjust the illumination intensity without considering the user preference in the related art.

[0033] In some embodiments of the present application, the target illumination intensity is determined based on the adjusted illumination intensity, which can be achieved by the following steps: obtaining an initial illumination intensity in the target area after adjusting the illumination intensity in the target area based on the regulation instruction; determining whether the initial illumination intensity belongs to a comfortable lighting intensity interval corresponding to the target area; and determining the initial illumination intensity as the target illumination intensity in the case that the initial illumination intensity belongs to the comfortable lighting intensity interval.

[0034] In some optional embodiments of the present application, the target illumination intensity is determined based on the adjusted illumination intensity, which further comprises the following steps: obtaining an initial illumination intensity in the target area after adjusting the illumination intensity in the target area based on the regulation instruction; determining whether the initial illumination intensity belongs to a comfortable lighting intensity interval corresponding to the target area; determining a deviation value corresponding to the initial illumination intensity in the case that the initial illumination intensity does not belong to the comfortable lighting intensity interval; determining a deviation level corresponding to the deviation value; adjusting the initial illumination intensity according to the deviation level, wherein the adjusted initial illumination intensity satisfies the comfortable lighting intensity interval; and determining the adjusted initial illumination intensity as the target illumination intensity.

[0035] In some embodiments of the present application, before determining whether the initial illumination intensity belongs to the comfortable lighting intensity interval corresponding to the target area, the satisfaction data of a plurality of objects in the target area can be acquired, wherein the satisfaction data is used to indicate the range of the acceptable illumination intensity of each object in the plurality of objects; and the satisfaction data is filtered to obtain the comfortable lighting intensity interval.

[0036] In some embodiments of the present application, the satisfaction data is screened to obtain a comfortable lighting range, which can be achieved through the following steps: calculating the range of acceptable light intensity for each object to obtain the maximum light intensity value and the minimum light intensity value of the acceptable light intensity range; and determining the set interval formed by the maximum light intensity value and the minimum light intensity value as the comfortable lighting range.

[0037] In some optional embodiments of the present application, after screening the satisfaction data and obtaining the comfortable lighting range, the comfortable lighting range can be determined as the first objective function, and the minimum operating cost can be determined as the second objective function; the lighting energy load is determined as the constraint conditions of the first objective function and the second objective function, and the comfortable lighting range and the operating cost are optimized.

[0038] Figure 2 This is a framework diagram of a load scheduling method for a public building lighting system in an optional public building lighting application scenario of this application, such as Figure 2 As shown in the figure, the framework mainly consists of five parts: environmental state space, comfortable lighting range, intelligent agent, reward and punishment function, and control device.

[0039] Figure 3 This is a flow chart of a load scheduling method for a public building lighting system based on reinforcement learning in an optional embodiment of the present application, such as Figure 3 As shown in the figure, the process mainly includes: reading environmental information, calculating instant reward and punishment values ​​and cumulative reward and punishment values, training through the intelligent agent neural network, selecting control instructions, judging whether the light intensity is adjusted based on the control instructions to meet the comfort requirements, and executing the control instructions and updating the environmental status when the comfort requirements are met; if the comfort requirements are not met, judging the deviation level and selecting the corresponding reward and punishment function, calculating the instant reward and punishment values ​​and cumulative reward and punishment values, training the intelligent agent neural network, selecting the control instructions again, executing the control instructions, and updating the environmental status.

[0040] Figure 4 This is an optional intelligent agent neural network structure diagram of this application, such as Figure 4 As shown in FIG, the neural network structure diagram includes: a convolutional layer and a fully connected layer. The environment state s is input and the environment state s is input into the neural network to obtain the state-action evaluation value function Q*(s,a).

[0041] Specifically, the above-mentioned public building lighting system scheduling method based on reinforcement learning may include the following steps:

[0042] Step 1: Divide public buildings into N lighting zones according to their functions, collect user satisfaction data on light intensity in these N zones, and establish comfortable lighting ranges for each zone.

[0043] Step 2: establish a load regulation target model that meets the comfort and has the minimum running cost and lighting load energy constraints;

[0044] Step 3: obtain the environmental state space parameters of the public building at time t, including indoor light intensity, time and real-time electricity price, and input the environmental state parameters to the lighting system agent;

[0045] Step 4: the lighting system agent integrates the immediate reward and punishment value obtained by the current action and the cumulative reward and punishment value, obtains the optimal state-action evaluation value of different states and different actions according to the Bellman optimal equation, and makes scheduling decisions on the lighting load regulation action according to the greedy strategy;

[0046] Step 5: calculate the regulation decision, judge whether the lighting result of each region meets the lighting comfort interval, if the region meets the lighting comfort interval, output the regulation decision value to the agent, if the region does not meet the lighting comfort interval, compare the simulation result of the region that does not meet the interval with the actual comfort interval of the region, judge the deviation level, and according to the deviation level, select the corresponding reward and punishment function again to repeat step 4, and output the regulation decision value to the agent.

[0047] Step 6: the agent executes the initial lighting load regulation action decision value, updates the state-action evaluation value function, and collects the environmental state of the public building at the next time.

[0048] Further, the comfort lighting interval of each region in step 1 is [l i.min ,l i.max ], l i.min is the minimum comfort lighting of the i-th region, and l i.max is the maximum comfort lighting of the i-th region.

[0049] Further, the comfort lighting interval of each region in step 1 is [l i.min ,l i.max ], l i.min is the minimum comfort lighting of the i-th region, and l i.max is the maximum comfort lighting of the i-th region.

[0050] Further, the load regulation target model that meets the comfort and has the minimum running cost in step 2 includes: a comfort load regulation target model and a load regulation target model with the minimum running cost. Wherein the comfort requirement is that the light intensity range of different regions of the public building is [l i.min ,l i.max ], at this time the light comfort punishment value is 0; when the light intensity of different regions of the public building is lower or higher than this interval, the deviation value is returned as the punishment value.

[0051] The deviation value is:

[0052] d = |l rt.i -l i |-Δl i

[0053]

[0054] l i =l i.min +Δl i

[0055] In the formula, l rt.i is the indoor light intensity of the i-th region at time t, l i.max and l i.min are the upper limit value and the lower limit value of the i-th region light comfort interval;

[0056] The comfort load regulation target model is:

[0057]

[0058]

[0059] The operation cost minimum load regulation target model:

[0060]

[0061] Energy (p t ) = c t × p t

[0062] In the formula, c t is the electricity price at time t, and p t is the power consumed by the lighting system lighting device in the public building at time t;

[0063] The step 2 lighting load energy constraint is:

[0064] 0 < p lt < p max

[0065] In the formula, p lt is the lighting system power consumption at time t, and p max is the maximum allowed lighting system power consumption.

[0066] Further, the environment state space s of the public building at any time t is:

[0067] s = {l rl , t, c t}

[0068] wherein, l rl is the light intensity in the room at time t, t is the current time t, and the electricity price is divided into five time periods, 0-8am is c1, 8-12am is c2, 12-17am is c3, 17-21am is c4, and 21-0am is c5, c t.i (i = 1, 2, 3, 4, 5) is the real-time electricity price at time t;

[0069] The public building lighting action discretization processing obtains a public building lighting action space a as:

[0070] a = {a1, a2,..., a n};

[0071] Further, the step 4 instant reward and punishment function at time t is:

[0072]

[0073] In the formula, μ is the penalty coefficient of energy consumption, γ i is the comfort penalty coefficient of the i-th area, ω1 and ω2 are function conversion coefficients;

[0074] The cumulative reward of the step 4 at any time after time t is:

[0075]

[0076] In the formula, μ is the decay coefficient;

[0077] The step 4 uses the Bellman optimal function to define the optimal state-action evaluation value calculation expression as:

[0078] Q * (s t ,a t ) = E[r(s t ,a t ) + αmaxQ * (s t+1 ,a t+1 )], α ∈ [0, 1]

[0079] In the formula, r(s t ,a t ) is the value of the reward and punishment function at time t, α is the reward value (which can be obtained by calculation), s t+1 is the environment state in the public building at time t+1, and a t+1 is the action of the public building lighting system at time t+1;

[0080] Referring to Figure 4As shown, according to the principle of reinforcement learning algorithm, the agent neural network is constructed.

[0081] The agent neural network takes the collected environmental state space parameters as the input of the neural network, and after the input is operated by the convolutional neural network and the fully connected neural network, the optimal state-action evaluation value Q is output. * t t .

[0082] The step 4 makes a regulation decision on the next time lighting load regulation action according to the greedy strategy:

[0083]

[0084] In the formula, is a set greedy value, q∈[0,1] is a random number generated by a computer, and a random is a random action value selected by the system.

[0085] Further, the step 5 is divided into three levels:

[0086] The first deviation interval is: [l i.min -Δl1,l i.min ]∪[l i.max ,l i.max +Δl1];

[0087] The second deviation interval is: [l i.min -Δl2,l i.min -Δl1]∪[l i.max +Δl1,l i.max +Δl2];

[0088] The third deviation interval is: [0, l i.min -Δl3]∪[l i.max +Δl3, l p ];

[0089] In the formula, Δl1, Δl2, Δl3 are deviation coefficients, l p is the rated lighting brightness of the lighting lamp;

[0090] The step 5 selects the corresponding three reward and punishment functions according to the deviation level:

[0091] The first reward and punishment function:

[0092]

[0093] The second reward and punishment function:

[0094]

[0095] ​​Three-level reward-punishment function:

[0096]

[0097] wherein μ1, μ2, μ3 are the penalty coefficients of energy consumption corresponding to the three levels respectively, γ 1.i ,γ 2.i γ 3.i are the comfort penalty coefficients of the i-th region corresponding to the three levels respectively, p t.i is the energy consumed by the i-th region at time t.

[0098] Further, the step 5 updates the state-action evaluation function as:

[0099] Q * (s t ,a t )←E[Q * (s t ,a t )+β(r(s t ,a t )+αmaxQ * (s t+1 ,a t+1 )-Q * (s t ,a t ))],α∈[0,1]

[0100] wherein β is the learning rate.

[0101] Figure 5 A device for determining illumination intensity according to an embodiment of the present application, as shown in FIG. 1, comprises: Figure 5

[0102] An acquisition module 40 is configured to acquire an environmental state space parameter in a target region, wherein the environmental state space parameter comprises at least indoor illumination intensity, a current time, and a real-time electricity price.

[0103] A first determination module 42 is configured to obtain an instant reward-punishment value and an accumulated reward-punishment value according to the environmental state space parameter.

[0104] A second determination module 44 is configured to obtain a control instruction according to the instant reward-punishment value and the accumulated reward-punishment value, wherein the control instruction is used to adjust the illumination intensity of a lighting device.

[0105] A third determination module 46 is configured to adjust the illumination intensity in the target region based on the control instruction, and determine a target illumination intensity based on the adjusted illumination intensity.

[0106] ​The light intensity determination apparatus, the acquisition module 40 is used for acquiring the current environment state space parameter in the target area, wherein the environment state space parameter at least includes: indoor light intensity, current time, and real-time electricity price; the first determination module 42 is used for obtaining the instant reward and punishment value and the cumulative reward and punishment value according to the environment state space parameter; the second determination module 44 is used for obtaining the control instruction according to the instant reward and punishment value and the cumulative reward and punishment value, wherein the control instruction is used for adjusting the light intensity of the lighting device; the third determination module 46 is used for adjusting the light intensity in the target area based on the control instruction, and determining the target light intensity based on the adjusted light intensity, so as to achieve the purpose of automatically adjusting the light intensity, thereby realizing the self-adjustment of the light intensity based on the environment state space parameter, saving the electric resource, and further solving the technical problems of affecting the normal work of the user, wasting the electric resource and affecting the user experience caused by setting the fixed threshold to adjust the light intensity in the related art without considering the user preference.

[0107] Optionally, the third determination module comprises: a first determination unit, configured to obtain the initial light intensity in the target area after adjusting the light intensity in the target area based on the control instruction; a judgment unit, configured to judge whether the initial light intensity belongs to the comfortable lighting degree interval corresponding to the target area; and a second determination unit, configured to determine the initial light intensity as the target light intensity in a case where the judgment result indicates that the initial light intensity belongs to the comfortable lighting degree interval.

[0108] According to another aspect of the embodiments of the present application, a nonvolatile storage medium is also provided, which comprises a stored program, wherein the program, when running, controls the device where the nonvolatile storage medium is located to perform any one of the light intensity determination methods.

[0109] Specifically, the storage medium is used for storing program instructions for executing the following functions to achieve the following functions:

[0110] acquiring the current environment state space parameter in the target area, wherein the environment state space parameter at least includes: indoor light intensity, current time, and real-time electricity price; obtaining the instant reward and punishment value and the cumulative reward and punishment value according to the environment state space parameter; obtaining the control instruction according to the instant reward and punishment value and the cumulative reward and punishment value, wherein the control instruction is used for adjusting the light intensity of the lighting device; adjusting the light intensity in the target area based on the control instruction, and determining the target light intensity based on the adjusted light intensity.

[0111] According to another aspect of the embodiments of the present application, a processor is also provided, which is used for running a program, wherein the program, when running, performs any one of the light intensity determination methods.

[0112] In particular, the processor is configured to invoke program instructions in the memory to implement the following functions:

[0113] obtaining an environment state space parameter in the target area, wherein the environment state space parameter comprises at least indoor illumination intensity, a current time, and a real-time electricity price; obtaining an instant reward and punishment value and an accumulated reward and punishment value according to the environment state space parameter; obtaining a control instruction according to the instant reward and punishment value and the accumulated reward and punishment value, wherein the control instruction is used to adjust the illumination intensity of the lighting device; adjusting the illumination intensity in the target area based on the control instruction, and determining a target illumination intensity based on the adjusted illumination intensity.

[0114] The sequence numbers of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

[0115] In the above-described embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0116] In the several embodiments provided by the present application, it should be understood that the disclosed technology can be implemented in other ways. Of course, the unit described as the division is only a logical function division, and there can be another division way during actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between each other can be indirect coupling or communication connection through some interface, unit or module, and can be electrical or other forms.

[0117] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple units. According to actual needs, part or all of the units can be selected to achieve the purpose of the present embodiment.

[0118] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0119] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0120] The above is only the preferred embodiment of the present application, and it should be pointed out that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should be considered as the protection scope of the present application.

Claims

1. A method of determining an intensity of illumination, characterized in that, The method comprises the following steps: obtaining current environmental state space parameters in a target area, wherein the environmental state space parameters at least include indoor illumination intensity, current time, and real-time electricity price; obtaining instant reward and punishment values and cumulative reward and punishment values according to the environmental state space parameters; obtaining control instructions according to the instant reward and punishment values and the cumulative reward and punishment values, wherein the control instructions are used to adjust the illumination intensity of a lighting device; adjusting the illumination intensity in the target area based on the control instructions, and determining a target illumination intensity based on the adjusted illumination intensity; wherein determining the target illumination intensity based on the adjusted illumination intensity comprises the following steps: obtaining an initial illumination intensity in the target area after adjusting the illumination intensity in the target area based on the control instructions; judging whether the initial illumination intensity belongs to a comfortable lighting intensity interval corresponding to the target area; in the case that the judgment result indicates that the initial illumination intensity belongs to the comfortable lighting intensity interval, determining that the initial illumination intensity is the target illumination intensity; in the case that the judgment result indicates that the initial illumination intensity does not belong to the comfortable lighting intensity interval, determining a deviation value corresponding to the initial illumination intensity; determining a deviation level corresponding to the deviation value; adjusting the initial illumination intensity according to the deviation level, wherein the adjusted initial illumination intensity satisfies the comfortable lighting intensity interval; and determining the adjusted initial illumination intensity as the target illumination intensity; wherein before judging whether the initial illumination intensity belongs to the comfortable lighting intensity interval corresponding to the target area, obtaining satisfaction data of a plurality of objects in the target area, wherein the satisfaction data is used to indicate the range size of the illumination intensity acceptable to each object in the plurality of objects; and filtering the satisfaction data to obtain the comfortable lighting intensity interval; filtering the satisfaction data to obtain the comfortable lighting intensity interval comprises the following steps: calculating the range size of the illumination intensity acceptable to each object to obtain a maximum illumination intensity value and a minimum illumination intensity value of the range size of the illumination intensity acceptable; and determining a set interval formed by the maximum illumination intensity value and the minimum illumination intensity value as the comfortable lighting intensity interval; after filtering the satisfaction data to obtain the comfortable lighting intensity interval, determining the comfortable lighting intensity interval as a first target function, determining the minimum running cost as a second target function, determining the lighting energy load as a constraint condition of the first target function and the second target function, and optimizing the comfortable lighting intensity interval and the running cost.

2. A device for determining the intensity of illumination, characterized in that The method comprises the following steps: an obtaining module is configured to obtain current environmental state space parameters in a target area, wherein the environmental state space parameters at least include indoor illumination intensity, current time, and real-time electricity price; a first determining module is configured to obtain instant reward and punishment values and cumulative reward and punishment values according to the environmental state space parameters; a second determining module is configured to obtain control instructions according to the instant reward and punishment values and the cumulative reward and punishment values, wherein the control instructions are used to adjust the illumination intensity of a lighting device; and The third determining module is configured to adjust the light intensity in the target area based on the regulation instruction, and determine a target light intensity based on the adjusted light intensity, wherein the determination of the target light intensity based on the adjusted light intensity comprises: obtaining an initial light intensity in the target area after the light intensity in the target area is adjusted based on the regulation instruction; determining whether the initial light intensity belongs to a comfortable lighting intensity interval corresponding to the target area; in a case where the determination result indicates that the initial light intensity belongs to the comfortable lighting intensity interval, determining that the initial light intensity is the target light intensity; in a case where the determination result indicates that the initial light intensity does not belong to the comfortable lighting intensity interval, determining a deviation value corresponding to the initial light intensity; determining a deviation level corresponding to the deviation value; adjusting the initial light intensity according to the deviation level, wherein the adjusted initial light intensity satisfies the comfortable lighting intensity interval; and determining the adjusted initial light intensity as the target light intensity; wherein, before the determination of whether the initial light intensity belongs to the comfortable lighting intensity interval corresponding to the target area, satisfaction data of a plurality of objects in the target area is obtained, wherein the satisfaction data is used to indicate a range size of an acceptable light intensity of each object in the plurality of objects; the satisfaction data is filtered to obtain the comfortable lighting intensity interval; the filtering of the satisfaction data to obtain the comfortable lighting intensity interval comprises: calculating the range size of the acceptable light intensity of each object to obtain a maximum light intensity value and a minimum light intensity value of the range size of the acceptable light intensity; and determining a set interval formed by the maximum light intensity value and the minimum light intensity value as the comfortable lighting intensity interval; after the filtering of the satisfaction data to obtain the comfortable lighting intensity interval, the comfortable lighting intensity interval is determined as a first objective function, and a minimum running cost is determined as a second objective function; and a lighting energy load is determined as a constraint condition of the first objective function and the second objective function, and the comfortable lighting intensity interval and the running cost are optimized.

3. The apparatus of claim 2, wherein, The third determining module comprises: a first determining unit configured to obtain an initial light intensity in the target area after the light intensity in the target area is adjusted based on the regulation instruction; a judging unit configured to determine whether the initial light intensity belongs to a comfortable lighting intensity interval corresponding to the target area; a second determining unit configured to, in a case where the determination result indicates that the initial light intensity belongs to the comfortable lighting intensity interval, determine that the initial light intensity is the target light intensity.

4. A non-volatile storage medium, characterized by, The non-volatile storage medium comprises a stored program, wherein the program controls a device in which the non-volatile storage medium is located to perform the light intensity determination method in any one of claims 1 when the program is executed.

5. A processor, comprising: The processor is configured to execute a program, wherein the program performs the light intensity determination method in any one of claims 1 when the program is executed.

Images