diff --git a/src/inference/dev_api/openvino/runtime/plugin_itt.hpp b/src/inference/dev_api/openvino/runtime/plugin_itt.hpp
new file mode 100644
index 00000000000..3c299c241d2
--- /dev/null
+++ b/src/inference/dev_api/openvino/runtime/plugin_itt.hpp
@@ -0,0 +1,21 @@
+// Copyright (C) 2018-2023 Intel Corporation
+// SPDX-License-Identifier: Apache-2.0
+//
+
+/**
+ * @brief Defines openvino domains for tracing
+ * @file plugin_itt.hpp
+ */
+
+#pragma once
+
+#include "openvino/itt.hpp"
+
+namespace ov {
+namespace itt {
+namespace domains {
+OV_ITT_DOMAIN(Plugin)
+OV_ITT_DOMAIN(PluginLoadTime)
+}  // namespace domains
+}  // namespace itt
+}  // namespace ov
diff --git a/src/inference/src/core.cpp b/src/inference/src/core.cpp
index a1efd394a0e..16ab7822c1c 100644
--- a/src/inference/src/core.cpp
+++ b/src/inference/src/core.cpp
@@ -5,7 +5,6 @@
 #include "openvino/runtime/core.hpp"
 
 #include "any_copy.hpp"
-#include "cnn_network_ngraph_impl.hpp"
 #include "dev/converter_utils.hpp"
 #include "dev/core_impl.hpp"
 #include "itt.hpp"
diff --git a/src/inference/src/dev/iremote_tensor.cpp b/src/inference/src/dev/iremote_tensor.cpp
index a1730ef4b1e..535ab38566e 100644
--- a/src/inference/src/dev/iremote_tensor.cpp
+++ b/src/inference/src/dev/iremote_tensor.cpp
@@ -4,13 +4,6 @@
 
 #include "openvino/runtime/iremote_tensor.hpp"
 
-#include <memory>
-
-#include "ie_blob.h"
-#include "ie_ngraph_utils.hpp"
-#include "ie_remote_blob.hpp"
-#include "openvino/runtime/properties.hpp"
-
 namespace ov {
 
 IRemoteTensor::~IRemoteTensor() = default;
diff --git a/src/inference/src/dev/isync_infer_request.cpp b/src/inference/src/dev/isync_infer_request.cpp
index 347d4925cd9..8e0f554fedd 100644
--- a/src/inference/src/dev/isync_infer_request.cpp
+++ b/src/inference/src/dev/isync_infer_request.cpp
@@ -7,7 +7,6 @@
 #include <memory>
 #include <unordered_map>
 
-#include "cpp_interfaces/plugin_itt.hpp"
 #include "openvino/core/except.hpp"
 #include "openvino/core/layout.hpp"
 #include "openvino/core/parallel.hpp"
@@ -16,6 +15,7 @@
 #include "openvino/runtime/iinfer_request.hpp"
 #include "openvino/runtime/iremote_context.hpp"
 #include "openvino/runtime/make_tensor.hpp"
+#include "openvino/runtime/plugin_itt.hpp"
 #include "openvino/runtime/tensor.hpp"
 
 namespace {
@@ -185,12 +185,12 @@ ov::SoPtr<ov::ITensor>& ov::ISyncInferRequest::get_tensor_ptr(const ov::Output<c
 }
 
 ov::SoPtr<ov::ITensor> ov::ISyncInferRequest::get_tensor(const ov::Output<const ov::Node>& port) const {
-    OV_ITT_SCOPED_TASK(InferenceEngine::itt::domains::Plugin, "get_tensor");
+    OV_ITT_SCOPED_TASK(ov::itt::domains::Plugin, "get_tensor");
     return get_tensor_ptr(port);
 }
 
 void ov::ISyncInferRequest::set_tensor(const ov::Output<const ov::Node>& port, const ov::SoPtr<ov::ITensor>& tensor) {
-    OV_ITT_SCOPED_TASK(InferenceEngine::itt::domains::Plugin, "set_tensor");
+    OV_ITT_SCOPED_TASK(ov::itt::domains::Plugin, "set_tensor");
     auto found_port = find_port(port);
     OPENVINO_ASSERT(found_port.found(), "Cannot find tensor for port ", port);
     try {
@@ -207,7 +207,7 @@ void ov::ISyncInferRequest::set_tensor(const ov::Output<const ov::Node>& port, c
 }
 
 std::vector<ov::SoPtr<ov::ITensor>> ov::ISyncInferRequest::get_tensors(const ov::Output<const ov::Node>& port) const {
-    OV_ITT_SCOPED_TASK(InferenceEngine::itt::domains::Plugin, "get_tensors");
+    OV_ITT_SCOPED_TASK(ov::itt::domains::Plugin, "get_tensors");
     auto found_port = find_port(port);
     OPENVINO_ASSERT(found_port.found(), "Cannot find input tensors for port ", port);
     if (found_port.is_input() && m_batched_tensors.count(get_inputs().at(found_port.idx).get_tensor_ptr()))
@@ -217,7 +217,7 @@ std::vector<ov::SoPtr<ov::ITensor>> ov::ISyncInferRequest::get_tensors(const ov:
 
 void ov::ISyncInferRequest::set_tensors(const ov::Output<const ov::Node>& port,
                                         const std::vector<ov::SoPtr<ov::ITensor>>& tensors) {
-    OV_ITT_SCOPED_TASK(InferenceEngine::itt::domains::Plugin, "set_tensors");
+    OV_ITT_SCOPED_TASK(ov::itt::domains::Plugin, "set_tensors");
     auto found_port = find_port(port);
     OPENVINO_ASSERT(found_port.found() && found_port.is_input(), "Cannot find input tensors for port ", port);
     if (tensors.size() == 1) {
diff --git a/src/inference/src/dev/plugin.hpp b/src/inference/src/dev/plugin.hpp
index 64f8ec67bc6..67a9d59b5e6 100644
--- a/src/inference/src/dev/plugin.hpp
+++ b/src/inference/src/dev/plugin.hpp
@@ -3,7 +3,7 @@
 //
 
 /**
- * @brief This is a header file for the Inference Engine plugin C++ API
+ * @brief This is a header file for the OpenVINO plugin C++ API
  *
  * @file plugin.hpp
  */
diff --git a/src/inference/src/infer_request.cpp b/src/inference/src/infer_request.cpp
index 02027935f2b..f48d6f0edea 100644
--- a/src/inference/src/infer_request.cpp
+++ b/src/inference/src/infer_request.cpp
@@ -6,10 +6,10 @@
 
 #include <map>
 #include <memory>
-#include <openvino/core/except.hpp>
 #include <string>
 
 #include "ie_common.h"
+#include "openvino/core/except.hpp"
 #include "openvino/core/node.hpp"
 #include "openvino/runtime/compiled_model.hpp"
 #include "openvino/runtime/exception.hpp"
diff --git a/src/inference/src/os/mac/mac_system_conf.cpp b/src/inference/src/os/mac/mac_system_conf.cpp
index 8133cbce66a..cb31d3676f1 100644
--- a/src/inference/src/os/mac/mac_system_conf.cpp
+++ b/src/inference/src/os/mac/mac_system_conf.cpp
@@ -44,7 +44,7 @@ int parse_processor_info_macos(int& _processors,
 
     _numa_nodes = 1;
     _sockets = 1;
-    
+
     if (sysctlbyname("hw.optional.arm64", &output, &size, NULL, 0) < 0) {
         _proc_type_table.resize(1, std::vector<int>(PROC_TYPE_TABLE_SIZE, 0));
         _proc_type_table[0][ALL_PROC] = _processors;