- 1Soltech 1STH-215-p solar PV module, 122
- Accountability, of personnel, 235
- Adam as optimizer, 220
- Adaptive neuro-fuzzy inference system (ANFIS), 162
- defuzzifying layer, 165
- fuzzifying layer, 164
- implication layer, 164
- normalization layer, 164
- output layer, 165
- Advanced metering infrastructure, 201
- Aggregation mechanisms, cluster-based, 82
- Agreement on Agriculture (AoA), WTO, 234
- AI, 183
- Air conditioners, discovery of, 212–213
- Air density, 181
- Amazon, 236
- Ami attack scenario,
- distributed denial of service, 204
- packet flooding, 204
- spoofing, 204
- ANN, 185
- Ant colony optimization, 103, 104
- AODV protocol, 81
- ARIMA, 185
- Artificial bee colony (ABC), 37, 58
- Artificial intelligence (AI), 37–38, 62, 183
- Artificial intelligence (AI) in production of biodiesel energy,
- biodiesel in India context, 233–234
- Indian perspective of renewable biofuels, 230–232
- opportunities, 232–233
- overview, 230
- proposed model, 234–236
- role, 235
- Artificial intelligence (AI)–based energy-efficient clustering and routing in IoT–assisted WSNs,
- clustering, 84–85
- overview, 80
- related study, 81–84
- research methodology, 85–88
- AI-based energy-aware routing protocol, 87–88
- clustering approach, 86–87
- WSN–based IoT environment, 85–86
- Artificial intelligence method, 158–160
- activation function, 161
- adoptive linear element neural network, 160
- feed-forward neural network (FFNN), 160
- mean, 161
- radial basis function neural network (RBFNN), 160
- recurrent neural network, 160
- ridgelet neural network, 160
- sigmoidal function, 161
- standard deviation, 161
- wavelet neural network, 161
- weights, 161
- Artificial neural network (ANN), 38
- Atmanirbhar Bharat, 232
- Autoencoders, 130, 139–140, 144
- Aviation turbine fuel (ATF), 232
- Back-propagation multilayer perceptron (MLP), 37
- Base station (BS), 81, 83
- Batch learning, 135, 136
- Battery SoC modeling using polynomial regression,
- current research in battery energy storage systems, 118
- dynamic battery modeling, 119–122
- block diagram for simulation setup, 120
- proposed methodology, 120–122
- first-order battery model, 119
- overview, 115–119
- results and discussion, 122–126
- Bayesian regularization (BR), 42
- Levenberg-Marquardt (LM), 37
- Bayesian ridge regression, forecasting of electricity consumption, 217, 220, 221
- Betz’s limit, 152
- Bias weights, 39
- Bidirectional LSTM, 181, 185, 194, 216, 219, 220, 221–222
- Bidirectional recurrent neural networks (BRNNs), 216, 219, 220, 221–222
- Bi-LSTM, 181–182, 185, 194, 197
- Biodiesel energy,
- AI in production of (see Artificial intelligence (AI) in production of biodiesel energy)
- classification, 230, 231
- cost of, 233–234
- ethanol, 232, 235, 236
- extraction in India, 235
- fish oil methyl ester, 232
- in commercial flights, 232
- in India context, 233–234
- Indian perspective of renewable biofuels, 230–232
- storage, 233
- Biomethanization, 94
- BLM, 185
- Blockchain technology, 235, 236
- Cadmium, in fabrication process, 117, 119
- Capacity,
- battery, 116
- current, 116
- payload, of vehicles, 117
- Carbon footprint, 115
- Carbon monoxide, 233
- Cluster heads (CHs),
- estimation, 80
- formation, 81, 82
- information of, 87
- lifetime of, 81
- selection, 81, 82, 84, 86, 87
- utilization of, 82
- Clustered WSNs, 84, 85
- Clustering, 168
- Clustering approach. see also Artificial intelligence (AI)–based energy-efficient clustering and routing in IoT-assisted WSNs,
- aggregation mechanisms, 82
- AI-based, 86–87
- communication process, 83
- distributed, 80
- dynamic, 80
- EPSO-CEO, 82
- GAECH, 82
- GEEC, 83
- hierarchical-based clustering nodes, 83
- in IoT applications, 83
- PSO-HC, 81
- routing protocols, 81
- in WSNs, 84–85
- Conventional statistical, 183
- Convolutional LSTM (ConvLSTM), 215–216, 219–222
- Convolutional neural network (CNN), 215–216
- Correlation, 168
- Correlation coefficient, 99
- Coulomb counting, 116
- Cut-in speed, 152
- Cut-off speed, 152
- Cyber attacks, 205
- Data falsification attacks, microgrid, 206
- Data falsification detection,
- machine learning, 206
- Markov model, 207
- Dataset preparation, forecasting of electricity consumption, 217–218
- Deep learning, 129–130, 132, 135, 137, 142
- Deep learning algorithms, 185
- Deep neural networks (DNNs), 116, 137, 143, 181
- Degree-constrained tree (DCT), 81
- Demand-driven scheme, 235
- Department of Land Records, 231
- Desertification and Land Degradation Atlas of India, 230–231
- Detection, 201–203, 205–207
- Dew point, 181
- Digitalization of services, 236
- Drones, 117
- DSR protocol, 81
- Dynamic battery modeling, 119–122
- Dynamic performance, 12
- Eigenvalues, 15
- Electric vehicles, 117
- Electricity consumption forecasting, for G20. see Forecasting of electricity consumption for G20
- E-NAM (National Agriculture Market) platform, 236
- Enerdata organization, 217
- Energy hole issue, 81
- Energy-efficient clustering and routing. see also Artificial intelligence (AI)–based energy-efficient clustering and routing in IoT-assisted WSNs,
- EEDAC-WSN, 83
- GEEC, 83
- LEACH protocol, 81, 83
- Energy-efficient data aggregation scheme for clustered WSN (EEDAC-WSN), 83
- Enhanced PSO-based clustering energy optimization (EPSO CEO) algorithm, 82
- Ensemble forecasting, 166
- Ensemble Kalman filter (EnKF), 37
- Ensemble models, 137, 139–140, 142, 144
- Epochs, 188, 191–192
- Equivalent circuit, 6, 7
- Ethanol, 232, 235, 236
- Evolutionary algorithms, 93, 96, 103, 106–110
- Extreme learning machine, 130, 137–138, 143
- False data injection, 201–202
- Feed forward neural networks, 213
- Feed forward network, 97
- Feed-forward algorithm, 37
- Feed-forward back-propagation, 37
- Firefly algorithm, 40, 51
- First node die (FND), 82
- Fish oil methyl ester, 232
- Fish-catching methods, AI-enabled, 232
- Fisheries,
- biodiesel production from, 233
- PMMSY, 233
- waste generated from, 232, 233
- Fisheries, and Aquaculture Infrastructure Development Fund (FIDF), 233
- Flat WSNs, 84
- Flipkart, 236
- Flux linkage per second, 5
- Forecast groundwater levels, 39
- Forecasting models, 129, 131–134, 138, 139, 143–144
- Forecasting of electricity consumption for G20,
- dataset preparation, 217–218
- history and advancement, 212–213
- overview, 211–217
- performance of all trained models, 219
- predictions done by models, 221–222
- recurrent neural networks, 213–216
- regression techniques,
- Bayesian ridge regression, 217, 220, 221
- linear regression, 216–217, 220, 221
- SVR, 217, 219, 220, 221
- requirement, 212
- results and discussions, 218–224
- statistical analysis of prediction done by LSTM model, 223–224
- training and test size for generated dataset, 218
- Forget gate, LSTM cell, 214
- Fuel price regulator, 235
- Fuzzy adaptive resonance theory mapping network with wavelet transform, 51
- Fuzzy ART (adaptive resonance theory), 37, 50
- Fuzzy logic, 185
- Game theory–based energy-efficient clustering routing protocol (GEEC), 82, 83
- Gated recurrent unit (GRU), 137, 139, 181, 185, 190, 214–215, 219–222
- Genetic algorithm, 103–104
- Genetic algorithm–based energy-efficient clustering hierarchy (GAECH), 82
- Genetic programming model, 40
- Geographic information system (GIS) mapping, 231, 235
- Global hunger index 2020, 234
- Gradient descent with momentum and adaptation learning rate back-propagation algorithm (GDX), 37
- Green gas emissions, 116
- GRU, 181, 185, 190–191, 197
- Half node die (HND), 82
- Hidden layer neurons, 45
- Hidden layers and neurons, 39
- Hierarchical clustering (HC), PSO protocol for, 81
- Hierarchical routing protocols, 82–83
- Hierarchical-based clustering nodes, 83
- Historical data, 158, 184
- HPCL, 232
- Huber as objective function, 220
- Humidity, 181, 184, 191
- Humpback whale activity, 39
- Hybrid method, 158
- Hybrid model, 183
- Hydraulic energy, 55
- Incremental learning, 135–136
- India,
- biodiesel, relevance of, 233–234
- biodiesel extraction in, 235
- biofuels in commercial flights, 232
- FIDF, 233
- IOCL and HPCL, 232
- ISPRL, 233
- Jamnagar refinery in Gujarat, 233
- Kharif, stubble burning of, 232
- marines and fisheries sector, 232–233
- National Biofuel Policy 2018, 232
- new farm bills, 232
- perspective of renewable biofuels, 230–232
- PMMSY, 233
- refining capacity of crude oil, 233
- Indian Strategic Petroleum Reserves Limited (ISPRL), 233
- Indigenous Indian Satellites, 231
- Induced tree of crossed cube (ITCC), 83
- Information, communication, and technology (ICT), 233
- Input gate, LSTM cell, 214
- Intended nationally determined contributions (INDC), 230
- Internet of things (IoT)–assisted WSNs, 83–84. see also Artificial intelligence (AI)–based energy-efficient clustering and routing in IoT-assisted WSNs
- Interval forecasting, 133–134, 140
- Intrusion detection system, 202
- IOCL, 232
- ISRO, 230, 231
- Jamnagar refinery in Gujarat, 233
- Jatropha Curcas, 231, 232, 235
- Kalman Filter technique, 116, 119, 121
- Kharif, stubble burning of, 232
- Last node die (LND), 82
- LCO (lithium cobalt oxide) battery, 117
- LEACH protocol, energy-efficient, 81, 83
- Lead acid, in fabrication process, 117, 119
- Levenberg-Marquardt (LM), 42
- Levenberge-Marquardt algorithm, 174
- LFP (lithium ion phosphate) battery, 117
- Linear regression, forecasting of electricity consumption, 216–217, 220, 221
- Linearization, 10
- Lithium cobalt oxide (LCO) battery, 117
- Lithium ion phosphate (LFP) battery, 117
- Lithium iron manganese phosphate (LiFeMnPO4) battery, 116
- Lithium, in fabrication process, 117, 119
- LM algorithm (LMA), 45
- Long short-term memory (LSTM), 130, 137–138, 143–144, 181, 184, 214–216, 219–224
- Long-term drought strategies, 40
- Long-term forecasting (LTF), 159
- LSSVM, 185
- LSTM, 181–182, 184, 186–188, 191, 197
- Machine learning (ML), forecasting of electricity consumption for G20 members using (see Forecasting of electricity consumption for G20)
- Machine learning algorithms, 185
- MAE, 181–182, 197
- Marine waste, 233
- Markov Chain Monte Carlo (MCMC) algorithm, 217
- MATLAB 2015b, 122
- Mean absolute deviation, 98
- Mean absolute error, 174–175, 181–182
- Mean square error, 98
- Medium-term forecasting (MTF), 159
- Mercury, in fabrication process, 117, 119
- Metaheuristic, 51–52, 70
- Methanogenesis, 94–95
- Methods of forecasting,
- MGNREGA (Mahatma Gandhi National Rural Employment Guarantee Act), 235
- Middle Awash Agricultural Development Enterprise (MAADE), 41
- Minimum support price (MSP), 231
- Ministry of Fisheries, Animal Husbandry, and Dairying, 232
- Mission innovation (MI) program, 233
- Modeling, 4, 38, 40, 42–44, 46–49, 51, 59–60, 63–66
- Modeling, SoC. see State of charge (SoC) modeling
- MSE, 182, 196–197
- Multi-hop routing protocols, 82
- Multilayer perceptron (MLP), 52
- Multi-objective forecasting, 133, 134
- Multiphase machine, 3
- Multiple-sink placement algorithm, 81
- Multi-step forecasting, 133–134, 142, 144
- Multi-task learning, 130, 135, 137, 142
- Mutual coupling, 6
- National Biofuel Policy, 232, 234
- Natural language processing, and forecasting, 213
- Neural networks (NNs), 52, 116, 183, 184
- Neural networks, RNNs, 213–216
- Neural structural learning, 136–137
- Nickel metal hydride, in fabrication process, 117, 119
- Nitrogen oxide (NOx) emissions, 233
- Nonlinear autoregressive exogenous (NARX), 37, 53
- Non-probabilistic algorithms, 85
- Normalization method, 48
- On-hole alert (OHA) protocol, 81
- On-hole children reconnection (OHCR) protocol, 81
- Open-circuit voltage (OCV), 117, 119, 125
- Optimization, 38–39, 48, 51, 55–57, 60, 62–63, 70, 73–76
- Output gate, LSTM cell, 214
- Packet drop, 205
- Parametric variation,
- damper winding, 22, 24
- field circuit, 19
- magnetizing reactance, 26
- stator, 16
- Paris Agreement, 230
- Particle swarm optimization, 103, 106–107
- Peak humidity, 45
- Perovskite solar cells, 116
- Persistence method, 158, 159
- Persistence model, 133
- Photovoltaic (PV) arrays, solar,
- Physical, 183
- Physical attacks, 205
- Physical method, 158
- advanced power curve models, 158
- numerical weather prognostication (NWP), 158
- statistical downscaling, 158
- Polynomial regression,
- Power coefficient, 150
- Pradhan Mantri Matsya Sampada
- Yojna (PMMSY), 233
- Prediction, 38–40, 42–45, 47–48, 51–55, 58–60, 62, 64, 66–68, 70–72
- Prediction framework, 155
- Pressure, 181, 191
- Probabilistic algorithms, 85
- Probabilistic forecasting, 133, 138, 144
- Process automation, AI in, 231
- PSO protocol for hierarchical clustering (PSO-HC), 81
- Python, 218
- Quality-of-service (QoS)–based routing protocols, 81
- Radial basis function neural network (RBFN), 37, 39
- Ramp forecasting, 133, 134
- Recurrent neural networks (RNNs), 213–216
- Regression techniques, forecasting of electricity consumption,
- Regression, polynomial,
- Reinforcement learning (RL) approach, 116
- ReLU as activation function, 220
- Renewable biofuels, Indian perspective of, 230–232
- Renewable energy, 38, 62, 148–149
- Renewable energy source (RES), 230
- Reset gate, GRU, 214
- Ring routing protocols, 82
- RMSE, 182, 196–197
- RNNs. see Recurrent neural networks (RNNs)
- Root mean square error, 99, 182
- Routing, in IoT–assisted WSNs. see also Artificial intelligence (AI)–based energy-efficient clustering and routing in IoT–assisted WSNs,
- AI-based energy-aware routing protocol, 87–88
- hierarchical routing protocols, 82–83
- problem, 81
- QoS–based routing protocols, 81
- ring routing protocols, 82
- routing protocols, security, 84
- Ryzen 5 4600H, 218
- Scene learning, 135–136, 143
- ScikitLearn, 218
- Sequential learning, 135–136
- Shark smell optimization (SSO), 37, 51
- Shortest-path tree (SPT), 81
- Short-term forecasting (STF), 159
- Sink nodes, 80–82, 84
- Six-phase synchronous machine, 4
- Smart grid, 201–205, 206–208
- Smart meter, 201–205, 207–208
- SoC (state of charge) modeling. see State of charge (SoC) modeling Solar irradiation, 49, 51, 68–70
- Solar panels, thin-film crystalline–based, 117
- Solar PV arrays,
- Solar radiation, 47–48, 51, 60, 66–70
- Solar-based PV cells, 116–117
- Space satellites, 117
- Spatial correlation, 183
- Speech recognition, 213
- Stability analysis, 15
- State of charge (SoC) modeling,
- battery, using polynomial regression (see Battery SoC modeling using polynomial regression)
- curve fitting for OCV-SoC, 125
- estimation, model parameters for, 123
- irradiance, current, voltage, and SoC for simulation setup, 124
- measurement and estimation, 116
- OCV and, 119
- Statistical method, 158
- Stochastic gradient descent (SGD), 169
- Support vector machine (SVM), 165
- hyperplane, 165
- soft margin, 165
- SVM kernels, 165
- Support vector machine (SVM) approach, 116
- Support vector regression (SVR), forecasting of electricity
- Sustainable energy, 230, 233, 237
- Sustainable energy sources, 115
- SVM, 185–186
- Taylor series expansion, 10
- Temperature, 181, 184, 191
- TensorFlow, 218
- Theil’s coefficient, 217
- Three-layer back-propagation network, 41
- Time series method, 158–159
- non-stationary time series, 159
- stationary time series, 159
- TORA protocol, 81
- Total geographical area (TGA), 231
- Transfer learning, 131, 135–136, 143
- Unemployment, urban, 235
- Update gate, GRU, 214
- Urban employment guarantee scheme (UEGS), 235
- Utilization and planning, 43
- Vapnik-Chervonenkis control model, 217
- Variation in load, 28
- Very short-term forecasting (VSTF), 159
- Viterbi algorithm, 207
- Voltage equations, 5
- Voronoi cell, 83
- Wasteland Atlas of India, 231
- Wavelet neural network (WNN), 37
- Wavelet soft threshold denoising (WSTD), 168
- Weakly connected dominating set (WCDS), 82
- WEMER protocol, 83
- Whale optimization algorithm (WOA), 37, 39
- Wind direction, 184
- Wind energy, 149–150
- Wind farms, 182
- Wind forecasting,
- long duration, 153
- short duration, 153
- Wind forecasting models,
- hybrid method, 155
- physical method, 154
- statistical method, 154
- Wind generation, 184
- Wind power, 184
- Wind prediction, 184
- Wind speed, 181–182, 184, 186, 191
- Wind turbines, 182–184
- Wireless sensor networks (WSNs), IoT-assisted,
- ad hoc topology used by, 84
- AI–based energy-efficient
- clustering in, 84–85
- creating, 85–86
- EEDAC-WSN, 83
- energy efficiency in, 83
- energy-efficient routing process in, 86–87
- flat and clustered networks, 84, 85
- IoT application, 83
- sensor nodes, 83–84
- Wireless sensor node, 83–84
- World Trade Organization (WTO), 234
..................Content has been hidden....................
You can't read the all page of ebook, please click
here login for view all page.