ANN MPPT | ANN Based MPPT for Solar PV Battery Powered BLDC Motor
ANN MPPT | ANN Based MPPT for Solar PV Battery Powered BLDC Motor
𝐈𝐧𝐭𝐫𝐨𝐝𝐮𝐜𝐭𝐢𝐨𝐧
The ANN Based MPPT for Solar PV Battery Powered BLDC Motor is a MATLAB/Simulink-based renewable energy drive system that combines a solar PV array, Artificial Neural Network Maximum Power Point Tracking, battery energy storage, DC–DC converters, and a Brushless DC motor.
The main objective is to extract maximum available power from the solar PV system while maintaining a stable 24 V DC bus for continuous BLDC motor operation.
In this system:
☀️ Solar PV is the primary energy source.
🧠 ANN MPPT determines the optimum PV operating voltage.
🔋 Battery supports the motor when PV power is insufficient.
⚡ A boost converter transfers maximum PV power to the DC bus.
🔄 A bidirectional DC–DC converter manages battery charging and discharging.
🌀 A three-phase inverter drives the BLDC motor.
🎯 The DC bus is regulated at approximately 24 V.
The model is useful for students, researchers, and engineers studying intelligent MPPT, renewable-powered motor drives, battery energy management, and DC microgrid control using MATLAB/Simulink.
𝐒𝐲𝐬𝐭𝐞𝐦 𝐎𝐯𝐞𝐫𝐯𝐢𝐞𝐰
The complete system contains the following major sections:
Solar PV array
ANN-based MPPT controller
Boost DC–DC converter
Battery energy storage
Bidirectional DC–DC converter
DC-link/DC bus
Three-phase inverter
BLDC motor
Hall-sensor-based electronic commutation
Battery control algorithm
Voltage and current measurement
Power measurement
Battery State of Charge monitoring
Main System Ratings
Parameter | Value |
BLDC motor rated voltage | 24 V |
BLDC motor rated power | ≈39–40 W |
Solar PV capacity | ≈100 W |
PV voltage at maximum power | ≈17 V |
PV current per panel at maximum power | ≈2.94 A |
Number of parallel PV panels | 2 |
Battery nominal voltage | 12 V |
Battery capacity | 100 Ah |
DC bus reference voltage | 24 V |
Motor load torque | 0.125 N·m |
Initial battery SOC | 50% |
The PV array is deliberately rated higher than the BLDC motor so that surplus solar energy can be used for battery charging.
𝐁𝐋𝐃𝐂 𝐌𝐨𝐭𝐨𝐫 𝐏𝐚𝐫𝐚𝐦𝐞𝐭𝐞𝐫𝐬
A small 24 V, approximately 40 W BLDC motor is considered for the simulation.
The motor parameters are entered in the MATLAB/Simulink BLDC machine model using the manufacturer's standard specifications.
BLDC Motor Parameter | Value |
Rated voltage | 24 V |
Rated speed | 3000 rpm |
Rated torque | 0.125 N·m |
Rated power | ≈39 W |
Rated current | 2.5 A |
Peak current | 7.5 A |
Peak torque | 0.375 N·m |
Torque constant | 0.05 N·m/A |
Line-to-line resistance | 1.35 Ω |
Line-to-line inductance | 0.9 mH |
Rotor inertia used in the model | ≈0.33 kg·cm² |
Back-EMF type | Trapezoidal |
After entering the manufacturer specifications, Simulink computes the corresponding internal machine parameters.
For example:
Computed Parameter | Approximate Value |
Stator phase resistance | 0.675 Ω |
Stator phase inductance | 0.45 mH |
The trapezoidal back EMF option is selected because it is appropriate for conventional BLDC motor operation.
𝐒𝐨𝐥𝐚𝐫 𝐏𝐕 𝐒𝐲𝐬𝐭𝐞𝐦
The BLDC motor requires approximately 40 W, while the PV system is designed for approximately 100 W.
This provides enough power to:
Supply the BLDC motor.
Compensate for converter losses.
Charge the battery when excess PV power is available.
PV Array Parameters
Parameter | Value |
Approximate power of one panel | 49–50 W |
Voltage at maximum power | ≈17 V |
Current at maximum power | ≈2.941 A |
Series-connected modules | 1 |
Parallel-connected modules | 2 |
Total PV capacity | ≈100 W |
Since the two PV modules are connected in parallel:
PV voltage remains approximately 17 V.
Available PV current increases to approximately 5.8–5.9 A under high irradiance.
Total PV power approaches 100 W under favorable operating conditions.
𝐀𝐍𝐍 𝐁𝐚𝐬𝐞𝐝 𝐌𝐏𝐏𝐓
The major intelligent control feature of this model is the Artificial Neural Network based Maximum Power Point Tracking controller.
The ANN continuously estimates the optimum PV operating voltage according to environmental conditions.
ANN MPPT Inputs
The neural network receives:
Solar irradiance
PV temperature
ANN MPPT Output
The ANN generates:
Reference PV voltage
The reference voltage represents the operating point at which the PV system should operate to obtain maximum available power.
Why Use ANN MPPT?
ANN MPPT can learn the nonlinear relationship among:
Solar irradiance
Cell temperature
PV voltage
Maximum power point
This makes ANN attractive for PV systems because the solar panel characteristics change continuously with environmental conditions.
𝐀𝐍𝐍 𝐌𝐏𝐏𝐓 𝐂𝐨𝐧𝐭𝐫𝐨𝐥 𝐏𝐫𝐨𝐜𝐞𝐬𝐬
The complete MPPT control sequence is:
Irradiance + Temperature
⬇
Trained Artificial Neural Network
⬇
Reference PV Voltage
⬇
Reference Voltage vs Actual PV Voltage
⬇
PI Controller
⬇
Duty Cycle
⬇
PWM Generator
⬇
Boost Converter IGBT
⬇
Maximum PV Power Extraction
Therefore, the ANN does not directly switch the power converter. Instead, it supplies the optimum voltage reference to the closed-loop converter controller.
𝐁𝐨𝐨𝐬𝐭 𝐂𝐨𝐧𝐯𝐞𝐫𝐭𝐞𝐫
The PV array produces approximately 17 V at its maximum power point, while the BLDC drive requires a 24 V DC bus.
A boost converter is therefore placed between the PV array and DC link.
Boost Converter Design Targets
Parameter | Approximate Rating |
PV input voltage | 17 V |
Required DC bus voltage | 24 V |
Converter power rating | ≈100 W |
Control method | ANN MPPT + PI + PWM |
The boost converter performs two important functions:
Raises the PV voltage toward the required DC-bus level.
Provides the power-electronic interface required for MPPT operation.
𝐁𝐚𝐭𝐭𝐞𝐫𝐲 𝐄𝐧𝐞𝐫𝐠𝐲 𝐒𝐭𝐨𝐫𝐚𝐠𝐞
A 12 V, 100 Ah battery is connected to the DC bus through a bidirectional DC–DC converter.
The battery has two operating modes.
Battery Mode | Operating Condition | Battery Power Direction |
Charging | PV power exceeds system demand | Energy flows into battery |
Discharging | PV power is insufficient | Battery supports DC bus and motor |
For the sign convention used in the simulation:
Negative battery power/current → charging
Positive battery power/current → discharging
This convention makes it easy to identify the operating state directly from simulation plots.
𝐁𝐢𝐝𝐢𝐫𝐞𝐜𝐭𝐢𝐨𝐧𝐚𝐥 𝐃𝐂–𝐃𝐂 𝐂𝐨𝐧𝐯𝐞𝐫𝐭𝐞𝐫
The battery voltage is approximately 12 V, whereas the common DC bus is regulated near 24 V.
The bidirectional converter therefore provides controlled energy transfer in both directions.
During Battery Discharging
Energy flows as:
Battery → Bidirectional Converter → DC Bus → Inverter → BLDC Motor
The converter operates to increase the battery-side voltage to the DC-bus level.
During Battery Charging
Energy flows as:
Solar PV → DC Bus → Bidirectional Converter → Battery
Excess solar power is stored in the battery.
𝐁𝐚𝐭𝐭𝐞𝐫𝐲 𝐂𝐨𝐧𝐭𝐫𝐨𝐥 𝐒𝐭𝐫𝐚𝐭𝐞𝐠𝐲
The primary purpose of the battery converter controller is to maintain the DC-link voltage at approximately 24 V.
The control process is:
DC Bus Voltage Measurement
⬇
Compare with 24 V Reference
⬇
Voltage Error
⬇
PI Controller
⬇
PWM Control
⬇
Bidirectional Converter Switching
⬇
Battery Charging / Discharging
This provides automatic power balancing between the PV system, battery, and BLDC motor.
𝐖𝐨𝐫𝐤𝐢𝐧𝐠 𝐏𝐫𝐨𝐜𝐞𝐬𝐬
The energy-management operation can be understood from two main conditions.
☀️ Condition 1: High Solar Power
When:
PV power > BLDC motor power requirement
the system:
Supplies the motor from solar PV.
Maintains the DC bus near 24 V.
Sends surplus energy to the battery.
Battery current becomes negative.
Battery SOC increases.
For example, when the PV system generates close to 100 W, only part of the energy is required by the motor drive. The remaining energy can charge the battery.
☁️ Condition 2: Reduced Solar Power
When solar irradiance decreases:
PV generation falls.
ANN MPPT adjusts the PV reference voltage.
The boost converter continues extracting available PV power.
If PV power becomes insufficient, the battery supplies the deficit.
Battery converter power changes from negative to positive.
BLDC motor operation continues.
This provides improved continuity of motor operation even during changes in solar irradiance.
𝐁𝐋𝐃𝐂 𝐌𝐨𝐭𝐨𝐫 𝐃𝐫𝐢𝐯𝐞
The regulated DC bus is connected to a three-phase inverter.
The inverter supplies the BLDC motor according to the rotor position information.
The motor control section includes:
Three-phase voltage-source inverter
BLDC motor
Hall signals
Hall-signal decoder
Gate-pulse generation
Stator current measurement
Back-EMF measurement
Rotor-speed measurement
Electromagnetic torque measurement
The Hall signals identify rotor position and determine the appropriate inverter switching sequence.
𝐒𝐢𝐦𝐮𝐥𝐚𝐭𝐢𝐨𝐧 𝐒𝐞𝐭𝐮𝐩
The system is tested under changing solar irradiance to observe the response of the ANN MPPT and battery energy-management system.
The narrated simulation particularly demonstrates operation at approximately:
1000 W/m²
600 W/m²
with irradiance changed during the simulation.
The motor load torque is maintained at approximately:
0.125 N·m
The initial battery SOC is approximately:
50%
𝐒𝐢𝐦𝐮𝐥𝐚𝐭𝐢𝐨𝐧 𝐑𝐞𝐬𝐮𝐥𝐭𝐬
Performance at 1000 W/m²
At high irradiance, the PV array operates close to its maximum available power.
Parameter | Approximate Result |
Solar irradiance | 1000 W/m² |
PV voltage | ≈17 V |
PV current | ≈5.8–5.9 A |
PV array power | ≈100 W |
PV converter output power | ≈95 W |
Battery current | ≈−2 A |
Battery converter power | ≈−35 W |
Load/inverter input power | ≈60 W |
DC-link voltage | ≈24 V |
Initial battery SOC | ≈50% |
Battery operating condition | Charging |
The negative battery current confirms that surplus PV energy is being stored in the battery.
The SOC increases slightly from approximately 50% to 50.006% during the illustrated simulation interval.
𝐑𝐞𝐬𝐩𝐨𝐧𝐬𝐞 𝐭𝐨 𝐑𝐞𝐝𝐮𝐜𝐞𝐝 𝐈𝐫𝐫𝐚𝐝𝐢𝐚𝐧𝐜𝐞
When irradiance decreases to approximately 600 W/m², PV generation falls significantly.
Parameter | High Irradiance | Reduced Irradiance |
Irradiance | 1000 W/m² | 600 W/m² |
PV power | ≈100 W | ≈60 W |
Battery current | ≈−2 A | ≈+1 A |
Battery power | Negative | Positive |
Battery mode | Charging | Discharging/supporting |
DC bus | ≈24 V | Regulated near 24 V |
Motor operation | Continuous | Continuous |
The most important observation is the automatic transition of the battery from charging mode to discharging/support mode.
This occurs without interrupting the BLDC motor operation.
𝐏𝐨𝐰𝐞𝐫 𝐅𝐥𝐨𝐰 𝐀𝐧𝐚𝐥𝐲𝐬𝐢𝐬
High PV Generation
PV → BLDC Motor + Battery Charging
Example:
PV converter output ≈ 95 W
Motor/inverter-side demand ≈ 60 W
Remaining power is directed toward battery charging, with converter losses accounting for the practical power balance.
Reduced PV Generation
PV + Battery → BLDC Motor
As PV generation decreases:
Available PV energy continues to supply part of the load.
Battery provides the remaining required power.
DC-link voltage remains controlled.
BLDC motor remains operational.
𝐂𝐨𝐧𝐭𝐫𝐨𝐥 𝐒𝐭𝐫𝐚𝐭𝐞𝐠𝐲
The complete model contains three coordinated control layers.
1. ANN MPPT Control
Responsible for:
Receiving irradiance and temperature.
Predicting optimum PV reference voltage.
Maximizing available solar power.
2. PV Boost Converter Control
Responsible for:
Tracking the ANN-generated reference.
Generating PWM duty cycle.
Controlling the boost converter.
3. Battery Converter Control
Responsible for:
Monitoring the DC-link voltage.
Maintaining approximately 24 V.
Automatically charging or discharging the battery.
Together, these controllers provide coordinated power management between the renewable source, storage system, and motor drive.
𝐊𝐞𝐲 𝐅𝐞𝐚𝐭𝐮𝐫𝐞𝐬
✅ Artificial Neural Network based MPPT
✅ Solar irradiance and temperature used as ANN inputs
✅ ANN-generated optimum PV voltage reference
✅ Approximately 100 W solar PV system
✅ 24 V, 40 W BLDC motor
✅ 12 V, 100 Ah battery
✅ PV boost converter
✅ Bidirectional battery DC–DC converter
✅ Closed-loop 24 V DC-bus regulation
✅ Automatic battery charging and discharging
✅ Hall-sensor-based BLDC commutation
✅ Variable-irradiance simulation
✅ PV voltage, current, and power monitoring
✅ Battery voltage, current, power, and SOC monitoring
✅ BLDC speed, torque, current, and back-EMF analysis
✅ MATLAB/Simulink implementation
𝐖𝐡𝐲 𝐭𝐡𝐞 𝐁𝐚𝐭𝐭𝐞𝐫𝐲 𝐢𝐬 𝐈𝐦𝐩𝐨𝐫𝐭𝐚𝐧𝐭
Solar PV generation is naturally dependent on environmental conditions.
Without battery support, sudden reduction in irradiance can cause:
DC-link voltage reduction
Motor-speed disturbance
Insufficient motor input power
Unstable drive performance
The battery compensates for these variations.
Therefore:
PV provides renewable energy → ANN extracts maximum available power → Battery balances the energy → DC bus remains regulated → BLDC motor continues operating.
𝐖𝐡𝐲 𝐀𝐍𝐍 𝐌𝐏𝐏𝐓 𝐢𝐬 𝐔𝐬𝐞𝐟𝐮𝐥
The PV operating point changes because of:
Irradiance variation
Temperature variation
Nonlinear PV characteristics
An ANN can be trained using PV operating data so that it learns the relationship between environmental conditions and the required MPP operating voltage.
Potential benefits include:
Fast reference generation
Nonlinear mapping capability
Simple online implementation after training
Reduced dependence on continuous perturbation
Convenient integration with digital converter control
Actual tracking performance still depends on the quality of the training dataset, ANN architecture, converter design, sampling time, and controller tuning.
𝐀𝐩𝐩𝐥𝐢𝐜𝐚𝐭𝐢𝐨𝐧𝐬
This type of solar PV–battery–BLDC architecture can be studied for:
☀️ Solar-powered DC motor drives
💧 Solar water pumping systems
🌾 Agricultural motor-drive systems
🔋 PV-battery energy-management systems
🌀 Renewable-powered BLDC drives
⚡ Low-voltage DC microgrids
🧠 Intelligent MPPT research
🚲 Small electric mobility systems
🏭 Energy-efficient DC motor applications
🎓 MATLAB/Simulink power-electronics learning and research
𝐖𝐡𝐚𝐭 𝐂𝐚𝐧 𝐁𝐞 𝐎𝐛𝐬𝐞𝐫𝐯𝐞𝐝 𝐢𝐧 𝐭𝐡𝐞 𝐒𝐢𝐦𝐮𝐥𝐚𝐭𝐢𝐨𝐧?
The Simulink model allows users to observe:
Solar PV
PV voltage
PV current
PV power
Converter current
Converter output power
Battery
Battery voltage
Battery current
Battery SOC
Battery converter power
Charging/discharging transitions
DC Bus
DC-link voltage
Input current to the inverter
Load power
BLDC Motor
Rotor speed
Electromagnetic torque
Stator current
Back EMF
This makes the model suitable for studying both the energy-management layer and the motor-drive layer.
𝐌𝐚𝐢𝐧 𝐎𝐛𝐬𝐞𝐫𝐯𝐚𝐭𝐢𝐨𝐧𝐬
The simulation demonstrates several important operating characteristics:
The ANN MPPT controller provides an optimum PV voltage reference based on environmental inputs.
The PV system produces close to its rated power under high irradiance.
Surplus PV energy charges the battery.
Reduction in irradiance decreases PV power.
The battery automatically changes from charging to discharging/support operation.
The DC-link voltage remains close to the required 24 V.
The BLDC motor continues operating despite solar-power variation.
The overall model demonstrates coordinated operation of PV, ANN MPPT, battery storage, power converters, and BLDC motor drive.
𝐂𝐨𝐧𝐜𝐥𝐮𝐬𝐢𝐨𝐧
The ANN Based MPPT for Solar PV Battery Powered BLDC Motor model demonstrates an intelligent renewable-energy motor-drive system using MATLAB/Simulink.
A solar PV array rated at approximately 100 W supplies a 24 V, approximately 40 W BLDC motor through an ANN-controlled boost converter. A 12 V, 100 Ah battery connected through a bidirectional converter provides energy balancing and helps regulate the common DC bus at approximately 24 V.
Under high solar irradiance, the PV system supplies the motor while surplus energy charges the battery. When irradiance decreases, the battery changes to discharging/support operation and compensates for the reduction in PV generation.
The model therefore provides a clear platform for understanding ANN MPPT, solar PV conversion, battery energy management, bidirectional converters, DC-link voltage control, and BLDC motor-drive operation.
Comments